Obstacle detection method and device, robot, and storage medium

Abstract

The application provides a specific obstacle detection method and device, a robot and a computer readable storage medium. The method comprises the following steps: detecting, by a collision sensor of the robot, that the robot collides in a target area; determining whether the obstacle in the target area can be identified by a laser radar of the robot; if the obstacle cannot be identified, determining that the obstacle in the target area is a specific obstacle; and the specific obstacle is a low obstacle or glass. According to the application, the specific obstacle in the working place of the robot can be accurately detected by the collision sensor and the laser radar under the condition of limited hardware cost.

Description

Technical Field

[0001] This application relates to the field of robotics, and in particular to a method and apparatus for detecting a specific obstacle, a robot, and a computer-readable storage medium. Background Technology

[0002] As people's living standards improve, the application of smart home appliances is becoming increasingly widespread, with robotic vacuum cleaners being a prime example. However, due to cost constraints, robotic vacuum cleaners are often equipped with fewer sensors or have insufficient sensor accuracy, making them unable to accurately detect certain obstacles (such as glass or low-lying obstacles). Currently, there is an urgent need for a solution that can identify specific obstacles under limited hardware conditions. Summary of the Invention

[0003] The purpose of this application is to provide a method and apparatus, robot, and computer-readable storage medium for detecting specific obstacles, so as to accurately detect specific obstacles.

[0004] On the one hand, this application provides a method for detecting a specific obstacle, including:

[0005] The robot's collision sensors detected a collision in the target area.

[0006] Determine whether the robot's lidar can identify obstacles in the target area;

[0007] If it cannot be identified, the obstacle in the target area is determined to be a specific obstacle; wherein, the specific obstacle is a low obstacle or glass.

[0008] In one embodiment, determining whether obstacles in the target area can be identified by the robot's lidar includes:

[0009] Determine whether the lidar can collect multiple laser points within the target area that can indicate the outline of the obstacle;

[0010] If possible, identify obstacles that can identify the target area;

[0011] If not, it is determined that the obstacle in the target area cannot be identified.

[0012] In one embodiment, the method further includes:

[0013] Once obstacles in the target area are identified, they are marked on a map of the robot's workplace based on the identification results.

[0014] In one embodiment, after determining that the obstacle in the target area is a specific obstacle, the method further includes:

[0015] When the robot collides with the target area, determine whether there are several target laser points with consecutive incident angles within the distance range between the lidar and the collision plate of the robot;

[0016] If present, determine whether the number of target laser points is less than a preset threshold.

[0017] If so, identify the specific obstacle as glass and mark it as glass on the map of the robot's workplace.

[0018] In one embodiment, the method further includes:

[0019] If it does not exist, the specific obstacle is identified as a low obstacle, and the specific obstacle is marked as a low obstacle in the map of the robot's workplace.

[0020] In one embodiment, detecting a collision between the robot and a target area using the robot's collision sensor includes:

[0021] When the robot's collision sensor is triggered, the robot is controlled to move along the edge of the collision side and turn to the collision side multiple times during the movement; wherein, the collision side is the side where the obstacle collides with the robot.

[0022] The collision sensor collects multiple consecutive collision points that collide with the collision side during the movement.

[0023] A target area is constructed on a map of the robot's workplace based on multiple consecutive collision points collected; wherein, the target area is the area where the robot collides.

[0024] In one embodiment, after determining that the obstacle in the target area is a specific obstacle, the method further includes:

[0025] The classification label prompt information of the target area is output to the user terminal; wherein the classification label prompt information indicates that the specific obstacle is classified and labeled.

[0026] On the other hand, this application provides a detection device for a specific obstacle, comprising:

[0027] The detection module is used to detect collisions between the robot and the target area using the robot's collision sensors.

[0028] The judgment module is used to determine whether the robot's lidar can identify obstacles in the target area;

[0029] The determination module is used to determine, if it cannot be identified, that the obstacle in the target area is a specific obstacle; wherein the specific obstacle is a low obstacle or glass.

[0030] Furthermore, this application provides a robot, the robot comprising:

[0031] processor;

[0032] Memory used to store processor-executable instructions;

[0033] The processor is configured to execute the aforementioned method for detecting specific obstacles.

[0034] In addition, this application also provides a computer-readable storage medium storing a computer program that can be executed by a processor to perform the above-described method for detecting specific obstacles.

[0035] This application's solution, with limited hardware costs, accurately detects specific obstacles in the robot's workplace using collision sensors and LiDAR; furthermore, by analyzing the distribution of laser points, the specific category of the obstacle can be identified, thus determining whether the obstacle is glass or a low obstacle; after identifying the specific obstacle, it is marked on the map of the robot's workplace, thereby helping the robot avoid the specific obstacle during subsequent work. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly described below.

[0037] Figure 1 This is a schematic diagram of the structure of a robot provided in one embodiment of this application;

[0038] Figure 2 A schematic flowchart illustrating a specific obstacle detection method provided in an embodiment of this application;

[0039] Figure 3 This is a schematic diagram of robot collision provided in one embodiment of this application;

[0040] Figure 4 A schematic diagram of laser emission provided in an embodiment of this application;

[0041] Figure 5 This is a schematic diagram of the distribution of laser dots provided in an embodiment of this application;

[0042] Figure 6 A flowchart illustrating a specific obstacle identification method provided in an embodiment of this application;

[0043] Figure 7A schematic diagram illustrating a specific obstacle identification method provided in an embodiment of this application;

[0044] Figure 8 A flowchart illustrating a method for constructing a target region according to an embodiment of this application;

[0045] Figure 9 This is a schematic diagram illustrating the movement of a robot colliding with an obstacle, provided in one embodiment of this application.

[0046] Figure 10 A flowchart illustrating a method for identifying a specific obstacle according to another embodiment of this application;

[0047] Figure 11 A block diagram of a specific obstacle detection device provided in an embodiment of this application. Detailed Implementation

[0048] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0049] Similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0050] like Figure 1 As shown, this embodiment provides a robot 1, including: at least one processor 11 and a memory 12. Figure 1 Taking a processor 11 as an example, the processor 11 and the memory 12 are connected via a bus 10. The memory 12 stores instructions that can be executed by the processor 11. The instructions are executed by the processor 11 to enable the robot 1 to perform all or part of the processes of the methods described in the following embodiments. In one embodiment, the robot 1 may be a sweeping robot, an inspection robot, etc., used to perform a method for detecting specific obstacles.

[0051] The memory 12 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0052] This application also provides a computer-readable storage medium storing a computer program that can be executed by a processor 11 to perform the specific obstacle detection method provided in this application.

[0053] When robots work in workplaces (such as residences or workshops) or map workplaces, they can identify obstacles within the workplace and mark them on the workplace map for subsequent obstacle avoidance. This application's solution can be used to detect specific obstacles such as glass and low-lying obstacles.

[0054] See Figure 2 This is a schematic flowchart illustrating a specific obstacle detection method provided in an embodiment of this application. Figure 2 As shown, the method may include the following steps 210-230.

[0055] Step 210: The robot's collision sensor detects that the robot has collided with the target area.

[0056] Among them, the collision sensor is used to detect the collision intensity when the robot collides with an obstacle. Therefore, the robot can detect collisions with itself during its movement based on the collision sensor.

[0057] The target area is the region in the workplace where the robot collides with obstacles. Therefore, obstacles exist in the target area.

[0058] During robot operation, when a collision plate in the robot's direction of movement encounters an obstacle, it can trigger the collision sensor on its own, enabling the robot to determine that it has collided at its current position and thus identify the target area.

[0059] Step 220: Determine whether the robot's lidar can identify obstacles in the target area.

[0060] LiDAR is used to emit laser light towards obstacles and receive the laser light reflected from them. The laser light reflected from obstacles can reveal their outlines, allowing the robot to identify the type of obstacle using the reflected light.

[0061] After identifying the target area, the robot can determine whether it can use LiDAR to collect multiple laser points within the target area that can indicate the outline of obstacles. In one scenario, if yes, the robot can identify obstacles in the target area. The robot can then identify obstacles in the target area based on the collected laser points. In another scenario, if no, the robot can determine that obstacles in the target area cannot be identified.

[0062] Step 230: If it cannot be identified, determine that the obstacle in the target area is a specific obstacle; wherein, the specific obstacle is a low obstacle or glass.

[0063] When obstacles in the target area cannot be identified by LiDAR, it can be determined that the obstacles in the target area are low obstacles or glass; in other words, the obstacles in the target area are specific obstacles.

[0064] See Figure 3 This is a schematic diagram of robot collision provided in an embodiment of this application. Figure 3 As shown in diagram a, 1 represents a low obstacle, 3 represents the robot body, 4 represents the robot's impact plate, and 5 represents the LiDAR. Figure 3 'a' represents a scenario where the robot collides with a low obstacle. In this case, the laser emitted by the lidar is higher than the low obstacle, so the laser will pass over the obstacle, and the robot cannot receive the reflected laser. For example... Figure 3 As shown in b, 2 represents glass, 3 represents the robot body, 4 represents the robot's impact plate, and 5 represents the LiDAR. Figure 3 'a' represents the scenario where the robot collides with the glass. In this case, most lasers will pass through the glass, and the robot will assume that there is no obstacle in front of it and continue to move forward until it hits the glass.

[0065] Through the above measures, even with limited hardware, accurate detection of specific obstacles can be achieved using only collision sensors and lidar.

[0066] In one embodiment, if obstacles in the target area can be identified using LiDAR, the robot can obtain the identification result after the obstacle is identified. The identification result can indicate the obstacle's category information. Based on the identification result, the robot can mark the identified obstacles on a map of the robot's workplace. Here, the map of the robot's workplace can be pre-built or gradually built as the robot moves. After marking the identified obstacles at the location of the target area on the map, the marked map contains the obstacle's location information and category information, enabling the robot to avoid collisions again in subsequent working processes.

[0067] In one embodiment, after determining that an obstacle in the target area is a specific obstacle, the robot can output classification labeling prompts for the target area to a user terminal. The user terminal can be a mobile phone, tablet, host computer, or other device. The classification labeling prompts instruct the user to classify and label the specific obstacle. The classification labeling prompts may include the location information of the target area within the robot's workspace, allowing the user terminal to display the target area on a map of the workspace and prompting the user to classify and label it.

[0068] After viewing specific obstacles in a target area, users can add markers to those obstacles via their user terminals. At this point, the specific obstacles in the target area on the map can be clearly marked as low-lying obstacles or glass.

[0069] Through the above measures, specific obstacles can be conveniently classified and marked with the help of human intervention, thereby reducing the workload of robots.

[0070] See Figure 4 This is a schematic diagram of laser emission provided in an embodiment of this application. Figure 4 a to Figure 4 b represents the process of the robot gradually approaching the obstacle. Figure 4 a and Figure 4 In diagram b, 2 represents a glass object in front of the robot's direction of movement, 6 represents a regular obstacle behind the glass, 3 represents the robot itself, 4 represents the robot's impact plate, and 5 represents the lidar. The vast majority of the laser emitted by the lidar passes through the glass. The laser that passes through the glass hits the regular obstacle behind the glass and reflects back. A small amount of laser light with a small angle of incidence hits the glass and reflects back to the lidar. As the robot moves forward, the closer it is to the glass, the more laser light passes through the glass, and the less laser light reflects back directly from the glass. Therefore, the robot will continue to move forward until its impact plate hits the glass.

[0071] When a robot collides with glass or low obstacles, a collision point can be generated on a map of the workplace, indicating the location where the robot collided with the obstacle. However, the collision point does not form a continuous obstacle outline, so LiDAR (Light Detection and Ranging) is needed for obstacle recognition. For specific obstacles, laser light can be used for classification, determining whether the obstacle is low or transparent glass. After the laser light reflects back from the obstacle to the LiDAR, the LiDAR can determine the location of the reflected laser light, which can be called the laser point.

[0072] See Figure 5 This is a schematic diagram of the distribution of laser points provided in an embodiment of this application. Figure 5 As shown in Figure a, 2 represents a glass object in front of the robot's direction of movement, 6 represents a common obstacle behind the glass, and 7 represents a laser point determined by the lidar based on the reflected laser light. Figure 5 In scenario a, only a small number of laser beams with small incident angles produce laser points located at the glass; the majority of laser points are distributed behind the glass where ordinary obstacles are located. For example... Figure 5 As shown in b, 1 is a low obstacle, 6 is a normal obstacle behind the low obstacle, and 7 is a laser point determined by the lidar based on the reflected laser light. Figure 5 In scenario b, since all the lasers emitted by the lidar pass over the low obstacles, there are no laser points on the low obstacles. All laser points are located on the ordinary obstacles behind the low obstacles.

[0073] The distribution of laser points that can be detected differs between low obstacles and glass, thus allowing for the classification of specific obstacles.

[0074] In one embodiment, see Figure 6 This is a flowchart illustrating a specific obstacle identification method provided in an embodiment of this application, as shown below. Figure 6 As shown, the method may include the following steps 610-630.

[0075] Step 610: Determine whether there are several target laser points with continuous incident angles within the distance range between the lidar and the collision plate of the robot when the robot collides in the target area.

[0076] The distance interval represents the minimum and maximum distances between the center point of the lidar and the edge of the impact plate. The target laser point is a continuous laser point with the corresponding incident angle within the distance interval. This incident angle is the angle at which the laser corresponding to the detected laser point hits the surface of the obstacle.

[0077] When a robot collides with an obstacle in a target area, it can determine whether several target laser points exist within a distance range. If none exist, the specific obstacle in the target area can be identified as a low-lying obstacle, and the robot can mark it as such on a map of its workspace. The robot can then mark the location and category information of this low-lying obstacle on the map. See also... Figure 5 b. Within the distance range, at the point where the impact plate collides with the obstacle, there is no laser point; therefore, the specific obstacle is a low obstacle. On the other hand, if it exists, step 620 can continue.

[0078] Step 620: If it exists, determine whether the number of target laser points is less than the preset number threshold.

[0079] Step 630: If so, identify the specific obstacle as glass and mark it as glass on the map of the robot's workplace.

[0080] The quantity threshold can be an empirical value used to distinguish between glass and ordinary obstacles.

[0081] When several target laser points with consecutive incident angles are within a distance interval, the robot can determine whether the number of target laser points is less than a threshold. On one hand, if it is not less than the threshold, it means that the obstacle in the target area can reflect enough laser light, and the obstacle is a common obstacle. On the other hand, if it is less than the threshold, it can be determined that the specific obstacle in the target area is glass, and the robot can mark the location and category information of this characteristic obstacle on the map.

[0082] See Figure 7 This is a schematic diagram of a method for identifying a specific obstacle provided in an embodiment of this application, as shown below. Figure 7 As shown, when a robot collides with an obstacle during its movement, collision points are generated, and multiple collisions can result in multiple collision points. These multiple collision points can constitute a target area on the map. During the collision process, multiple laser points can also be detected by LiDAR. Based on the distribution of these laser points, it can be determined whether the obstacle in the target area is glass or a low obstacle, and then marked on the map.

[0083] By implementing the above measures, the distribution of laser points can accurately distinguish between glass and low-lying obstacles when encountering specific obstacles.

[0084] In one embodiment, the robot can determine the target area where the obstacle is located based on the collision point after colliding with it during movement. See also Figure 8 This is a flowchart illustrating a method for constructing a target region according to an embodiment of this application, as shown below. Figure 8 As shown, the method may include the following steps 810-830.

[0085] Step 810: When the robot's collision sensor is triggered, control the robot to move along the edge of the collision side and turn to the collision side multiple times during the movement; where the collision side is the side where the obstacle collides with the robot.

[0086] When a robot moves within the workplace and collides with an obstacle, the collision sensor is triggered. At this point, the robot can determine that an obstacle exists in its direction of movement. The robot can then control itself to move along the edge of the side of the collision.

[0087] See Figure 9 This is a schematic diagram illustrating the movement of a robot colliding with an obstacle according to an embodiment of this application. Figure 9 As shown, after the robot encounters glass or a low obstacle, it can turn left and continue moving along the edge of the obstacle on the side of the collision.

[0088] During movement, the robot can turn towards the collision side multiple times, and if another collision occurs, the robot can turn again to move along the edge of the collision side, repeating this process multiple times, thus causing multiple collisions with the obstacle. Figure 9 As shown, during the movement from position 1 to position 4, the robot can collide with obstacles while moving along the edge of the obstacles.

[0089] Step 820: Collect multiple consecutive collision points that collide with the collision side during the motion using collision sensors.

[0090] After a collision with an obstacle, the collision point can be detected by a collision sensor. Multiple consecutive collision points can be detected during movement along the edge of the collision side.

[0091] Step 830: Construct a target area on the map of the robot's workplace based on the collected multiple consecutive collision points; wherein, the target area is the area where the robot collides.

[0092] After acquiring multiple consecutive collision points, the robot can construct a target region based on these points, indicating the obstacle's location on the map. If the robot moves along one side of the obstacle and acquires multiple consecutive collision points, the target region represents a line segment along one side of the obstacle. If the robot moves around the perimeter of the obstacle and acquires multiple consecutive collision points, the target region represents the overall location of the obstacle on the map.

[0093] Through the above measures, the robot can detect the location of obstacles on the map during movement and then identify the obstacles. Furthermore, in this application, the target area detection process can be progressively improved. During the execution of steps 210 to 230, an initial target area is determined as soon as an obstacle is encountered, thus determining whether the obstacle in the target area is a specific obstacle. However, when performing the specific obstacle identification process in steps 610 to 630, because the distribution of laser points is required, multiple collisions with the obstacle can be performed to generate a target area that more accurately represents the obstacle's location.

[0094] To illustrate the overall process of this solution, Figure 10 A flowchart illustrating a method for identifying a specific obstacle according to another embodiment of this application is shown below. Figure 10 As shown, during movement, the robot's collision sensors detect collisions. In this case, if the LiDAR cannot identify the obstacle at the collision location, it can be determined that the obstacle is a specific obstacle. One approach is to send classification and labeling prompts to the user terminal, allowing manual labeling of the specific obstacle. Another approach is for the robot to repeatedly collide with the obstacle to collect multiple collision points, and then use the LiDAR to collect the laser points at the time of the collision. The robot can determine if a small number of laser points match the collision point locations. In one case, if so, the specific obstacle can be identified as glass. In another case, if not, the specific obstacle can be identified as a low-lying obstacle. The robot can fit the shape of the obstacle based on multiple collision points, and then label the specific obstacle on a map based on the overall position information obtained from the fitting and the identified category.

[0095] Figure 11 This is a block diagram of a specific obstacle detection device according to an embodiment of the present invention, such as... Figure 11 As shown, the device may include:

[0096] The detection module 1110 is used to detect a collision between the robot and the target area using the robot's collision sensor;

[0097] The judgment module 1120 is used to determine whether the robot's lidar can identify obstacles in the target area;

[0098] The determination module 1130 is used to determine, if it cannot be identified, that the obstacle in the target area is a specific obstacle; wherein the specific obstacle is a low obstacle or glass.

[0099] The specific implementation process of the functions and roles of each module in the above-mentioned device can be found in the implementation process of the corresponding steps in the above-mentioned method for detecting specific obstacles, and will not be repeated here.

[0100] The apparatuses and methods disclosed in the several embodiments provided in this application can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatuses, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0101] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0102] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

Claims

1. A method for detecting a specific obstacle, characterized in that, include: The robot's collision sensors detected a collision in the target area. Determine whether the robot's lidar can identify obstacles in the target area; If it cannot be identified, the obstacle in the target area is determined to be a specific obstacle; wherein, the specific obstacle is a low obstacle or glass; After determining that the obstacle in the target area is a specific obstacle, the method further includes: determining whether there are several target laser points with consecutive incident angles within the distance range between the lidar and the robot's collision plate when the robot collides in the target area; if so, determining whether the number of the target laser points is less than a preset number threshold; if so, determining that the specific obstacle is glass, and marking the specific obstacle as glass in the map of the robot's workplace; In this process, some of the laser emitted by the lidar passes through the glass, and the laser that passes through the glass can be reflected back by ordinary obstacles behind the glass. In addition, some lasers with small incident angles are reflected back to the lidar by the glass. Furthermore, as the robot moves forward, the closer it is to the glass, the more lasers pass through the glass, and the less lasers are directly reflected back from the glass.

2. The method for detecting a specific obstacle according to claim 1, characterized in that, The determination of whether obstacles in the target area can be identified by the robot's lidar includes: Determine whether the lidar can collect multiple laser points within the target area that can indicate the outline of the obstacle; If possible, identify obstacles that can identify the target area; If not, it is determined that the obstacle in the target area cannot be identified.

3. The method for detecting a specific obstacle according to claim 2, characterized in that, The method further includes: When obstacles in the target area can be identified, the identified obstacles are marked on the map of the robot's workplace based on the identification results.

4. The method for detecting a specific obstacle according to claim 1, characterized in that, The method further includes: If it does not exist, the specific obstacle is identified as a low obstacle, and the specific obstacle is marked as a low obstacle in the map of the robot's workplace.

5. The method for detecting a specific obstacle according to claim 1, characterized in that, The detection of a collision between the robot and the target area using the robot's collision sensors includes: When the robot's collision sensor is triggered, the robot is controlled to move along the edge of the collision side and turn to the collision side multiple times during the movement; wherein, the collision side is the side where the obstacle collides with the robot. The collision sensor collects multiple consecutive collision points that collide with the collision side during the movement. A target area is constructed on a map of the robot's workplace based on multiple consecutive collision points collected; wherein, the target area is the area where the robot collides.

6. The method for detecting a specific obstacle according to claim 1, characterized in that, After determining that the obstacle in the target area is a specific obstacle, the method further includes: The classification label prompt information of the target area is output to the user terminal; wherein the classification label prompt information indicates that the specific obstacle is classified and labeled.

7. A device for detecting a specific obstacle, characterized in that, include: The detection module is used to detect collisions between the robot and the target area using the robot's collision sensors. The judgment module is used to determine whether the robot's lidar can identify obstacles in the target area; A determination module is used to determine, if it cannot be identified, that the obstacle in the target area is a specific obstacle; wherein, the specific obstacle is a low obstacle or glass; The determining module is further configured to: after determining that the obstacle in the target area is a specific obstacle, determine whether there are several target laser points with consecutive incident angles within the distance range between the lidar and the robot's collision plate when the robot collides in the target area; if so, determine whether the number of target laser points is less than a preset number threshold; if so, determine that the specific obstacle is glass, and mark the specific obstacle as glass in the map of the robot's workplace; In this process, some of the laser emitted by the lidar passes through the glass, and the laser that passes through the glass can be reflected back by ordinary obstacles behind the glass. In addition, some lasers with small incident angles are reflected back to the lidar by the glass. Furthermore, as the robot moves forward, the closer it is to the glass, the more lasers pass through the glass, and the less lasers are directly reflected back from the glass.

8. A robot, characterized in that, The robot includes: processor; Memory used to store processor-executable instructions; The processor is configured to perform the method for detecting a specific obstacle as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that can be executed by a processor to perform the method for detecting a specific obstacle as described in any one of claims 1-6.

Images