Sensor noise detection method, apparatus, robot, and storage medium

Abstract

The application relates to a sensor noise detection method and device, a robot, a storage medium and a computer program product. The method comprises the following steps: collecting a target environment by a sensor arranged on a robot, and obtaining first obstacle information; generating a first cost map according to the first obstacle information; if there is obstacle point cloud in a first target map region of the first cost map, determining that there is a noisy sensor in the sensor of the robot; the first target map region is a region in the first cost map representing a target region in the target environment; and no obstacle exists in the target region. The method can improve the efficiency of sensor noise detection.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a sensor noise detection method, apparatus, robot, storage medium, and computer program product. Background Technology

[0002] With the development of computer technology, robots are widely used in production and daily life. Robots typically carry multiple sensors for environmental perception and detection, collecting information about obstacles in their surroundings and using this information for obstacle avoidance. Random abnormal observations detected by the sensors, i.e., noise, can cause the robot to stutter during movement. Therefore, how to detect noise from the multiple sensors installed on a robot has become a crucial issue. Traditional techniques require sequential testing of each sensor. Only after all sensors have been tested can the overall sensor noise of the robot be determined, a process that is time-consuming and inefficient. Summary of the Invention

[0003] Therefore, it is necessary to provide a sensor noise detection method, apparatus, computer-readable storage medium, and computer program product that can improve detection efficiency in response to the above-mentioned technical problems.

[0004] Firstly, this application provides a sensor noise detection method. The method includes:

[0005] The robot collects information about the target environment using sensors deployed throughout the robot, thus obtaining information about the first obstacle.

[0006] A first cost map is generated based on the first obstacle information;

[0007] If there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region.

[0008] Secondly, this application also provides a sensor noise detection device. The device includes:

[0009] The data acquisition module is used to collect data from the target environment through sensors deployed throughout the robot to obtain information about the first obstacle.

[0010] The generation module is used to generate a first cost map based on the first obstacle information;

[0011] The determination module is used to determine that if there is an obstacle point cloud in the first target map region of the first cost map, there is a noisy sensor among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region.

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

[0013] The acquisition module is used to acquire the point cloud type of the obstacle point cloud in the first target map region;

[0014] The determining module is further configured to determine the noisy sensor based on the comparison result between the point cloud type and a preset point cloud type.

[0015] In one embodiment, the apparatus further includes:

[0016] The acquisition module is also used to, in response to a single sensor detection operation, acquire information about the target environment through the single sensor if a warning signal is received, to obtain second obstacle information;

[0017] The generation module is further configured to generate a second cost map based on the second obstacle information;

[0018] The determining module is further configured to determine that the single sensor has noise if there is an obstacle point cloud in the second target map region of the second cost map; the second target map region is the region in the second cost map that represents the target region in the target environment.

[0019] In one embodiment, the apparatus further includes:

[0020] The switching module is used to switch to another single sensor if there is no obstacle point cloud in the second target map area of ​​the second cost map;

[0021] The acquisition module is also used to acquire information about the target environment through the other single sensor to obtain information about the third obstacle;

[0022] The generation module is also used to generate a third cost map based on the third obstacle information;

[0023] The determining module is further configured to determine that the other single sensor has noise if there is an obstacle point cloud in the third target map region of the third cost map; the third target map region is the region in the third cost map that represents the target region in the target environment.

[0024] In one embodiment, the apparatus further includes:

[0025] The display module is used to display the first cost map on the sensor noise detection interface;

[0026] The determining module is further configured to, if there are obstacle point clouds in the first target map region of the first cost map, determine that there are noisy sensors among the sensors of the robot as a whole, including:

[0027] The determining module is further configured to determine that if there are obstacle point clouds in the first target map area displayed by the sensor noise detection interface, there are noisy sensors among the sensors of the robot as a whole.

[0028] In one embodiment, the apparatus further includes:

[0029] The determining module is further configured to determine that the sensors of the robot are free of noise if there is no obstacle point cloud in the first target map area.

[0030] Thirdly, this application also provides a robot. The robot includes a memory and a processor, the memory storing computer-readable instructions executable on the processor, and the processor executing the computer-readable instructions to perform the following steps:

[0031] The robot collects information about the target environment using sensors deployed throughout the robot, thus obtaining information about the first obstacle.

[0032] A first cost map is generated based on the first obstacle information;

[0033] If there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map used to represent the target region in the target environment; there are no obstacles in the target region.

[0034] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0035] The robot collects information about the target environment using sensors deployed throughout the robot, thus obtaining information about the first obstacle.

[0036] A first cost map is generated based on the first obstacle information;

[0037] If there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0039] The robot collects information about the target environment using sensors deployed throughout the robot, thus obtaining information about the first obstacle.

[0040] A first cost map is generated based on the first obstacle information;

[0041] If there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region.

[0042] The aforementioned sensor noise detection method, apparatus, robot, storage medium, and computer program product collect data from the target environment using sensors deployed throughout the robot, obtain first obstacle information, and generate a first cost map based on this first obstacle information. If obstacle point clouds are present in the first target map region of the first cost map, it is determined that noisy sensors exist within the robot's overall sensor suite. The first target map region is the area in the first cost map that represents the target area where no obstacles exist in the target environment. Since no obstacles exist in the target area, if none of the robot's sensors are noisy, obstacle point clouds representing obstacles will not appear in the first target map region of the first cost map generated based on the first obstacle information. Therefore, the presence of obstacle point clouds in the first target map region indicates that the first obstacle information collected by the sensors contains abnormal observations, meaning that noisy sensors exist within the robot's overall sensor suite. This eliminates the need to sequentially detect each sensor, allowing for rapid determination of whether the robot's sensors are noisy, thus improving the efficiency of sensor detection for the entire robot. Attached Figure Description

[0043] Figure 1 This is an application environment diagram of the sensor noise detection method in one embodiment;

[0044] Figure 2 This is a flowchart illustrating a sensor noise detection method in one embodiment;

[0045] Figure 3 This is a schematic diagram of the target environment in one embodiment;

[0046] Figure 4 This is a schematic diagram of a cost map in one embodiment;

[0047] Figure 5 This is a flowchart illustrating the sensor noise detection method in another embodiment;

[0048] Figure 6 This is a schematic diagram of the sensor noise detection interface in one embodiment;

[0049] Figure 7 This is a flowchart illustrating the sensor noise detection method in yet another embodiment;

[0050] Figure 8 This is a structural block diagram of a sensor noise detection device in one embodiment;

[0051] Figure 9 This is a structural block diagram of a sensor noise detection device in one embodiment;

[0052] Figure 10 This is a diagram of the internal structure of a robot in one embodiment. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] The sensor noise detection method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, robot 102 collects data on the target environment through sensors deployed throughout the robot to obtain first obstacle information; it generates a first cost map based on the first obstacle information; if there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the robot's sensors; the first target map region is the region in the first cost map that represents the target area in the target environment; there are no obstacles in the target area. Robot 102 can be, but is not limited to, various service robots, cleaning robots, or food delivery robots, etc.

[0055] In one embodiment, such as Figure 2 As shown, a sensor noise detection method is provided, which can be applied to... Figure 1 Taking the robot in the example, the following steps are included:

[0056] S202 collects information about the target environment through sensors deployed throughout the robot to obtain information about the first obstacle.

[0057] Sensors are electronic devices used to detect obstacles, and can be radar or depth sensors, etc. A robot can deploy multiple sensors; for example, it can deploy radar, depth sensors to detect suspended obstacles, and depth sensors to detect low-lying obstacles. The robot uses sensors to perceive and detect obstacles in the target environment, collecting obstacle information. Obstacle information indicates the relative position between the robot and the obstacle, including the distance between the robot and the obstacle, and the direction of the obstacle. For example, obstacle information might be "30 degrees in the direction of the obstacle, 2 meters away." The first obstacle information is the obstacle information collected by all the sensors deployed on the robot. For example, if the robot deploys radar, depth sensor 1, and depth sensor 2, the first obstacle information includes all obstacle information collected by radar, depth sensor 1, and depth sensor 2.

[0058] The target environment is the environment in which the robot operates, and can be an indoor or outdoor environment, etc. In one embodiment, before S202, the robot moves to a target area in the target environment where there are no obstacles. For example, ... Figure 3 As shown, the robot moves to a rectangular area in the target environment that is free of obstacles. In one embodiment, the target area can be a rectangular area 2 meters in front of the robot and 0.4 meters to the left and right.

[0059] In one embodiment, in response to a whole-machine sensor detection operation triggered in the noise detection interface, the robot collects data on the target environment using sensors deployed throughout the robot to obtain first obstacle information. The whole-machine sensor detection operation is used to perform noise detection on the sensors deployed throughout the robot, and can be triggered by clicking, swiping, or dragging a control.

[0060] S204, Generate a first cost map based on the first obstacle information.

[0061] The cost map is a map used to represent the target environment. For example... Figure 4 As shown, the cost map displays point clouds of the robot and obstacles, with the obstacle point clouds representing obstacles in the target environment. The first cost map is generated based on the first obstacle information and may include multiple layers, each generated based on obstacle information collected by a sensor. For example, layer 1 in the first cost map is generated based on obstacle information collected by radar, and its obstacle point clouds represent obstacles detected by the radar; layer 2 is generated based on obstacle information collected by a depth sensor, and its obstacle point clouds represent obstacles detected by the depth sensor. Figure 4 As shown, gray point clouds represent obstacles detected by radar, while white point clouds represent obstacles detected by depth sensors.

[0062] S206, if there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region.

[0063] The first target map region is the region in the first cost map that represents the target area in the target environment. For example, the first target map region could be the rectangular area in front of the robot in the first cost map. The target area is the area in the target environment where there are no obstacles, for example, such as... Figure 3 As shown, the target area is a rectangular region in front of the robot, where there are no obstacles. An obstacle point cloud is a set of pixels representing obstacles. The robot determines the position coordinates of obstacles based on the first obstacle information collected by sensors, and generates an obstacle point cloud in the first cost map based on these coordinates.

[0064] Since there are no obstacles in the target area, if none of the robot's sensors are no longer noisy, then no obstacle point cloud representing obstacles will appear in the first target map area of ​​the first cost map generated based on the first obstacle information. Therefore, the presence of obstacle point clouds in the first target map area indicates that the first obstacle information collected by the sensors contains abnormal observations, meaning that there are noisy sensors among the robot's sensors. This noisy sensor can be any sensor deployed on the robot, and can be one or more sensors.

[0065] In one embodiment, after S206, the method further includes: if the warning function is activated, a warning is issued when it is determined that there is a noisy sensor among the sensors of the robot as a whole, and the warning method includes sound warning, light flashing warning, etc.

[0066] In the above embodiments, sensors deployed throughout the robot collect data on the target environment to obtain first obstacle information; a first cost map is generated based on the first obstacle information; if obstacle point clouds are present in the first target map region of the first cost map, it is determined that noisy sensors exist among the robot's sensors; the first target map region is the region in the first cost map that represents the target area where no obstacles exist in the target environment. Since there are no obstacles in the target area, if none of the robot's sensors are noisy, obstacle point clouds representing obstacles will not appear in the first target map region of the first cost map generated based on the first obstacle information. Therefore, the presence of obstacle point clouds in the first target map region indicates that the first obstacle information collected by the sensors contains abnormal observations, meaning that noisy sensors exist among the robot's sensors. This eliminates the need to sequentially test each sensor, allowing for rapid determination of whether the robot's sensors are noisy, thus improving the efficiency of sensor testing for the entire robot.

[0067] In one embodiment, after S206, the method further includes: acquiring the point cloud type of the obstacle point cloud in the first target map region; and determining the noisy sensor based on the comparison result between the point cloud type and a preset point cloud type.

[0068] The point cloud type refers to the type of obstacle point cloud, including various colors, shapes, and other types. The robot can pre-set the point cloud type for each sensor's obstacle point cloud. For example, the robot can configure the point cloud type for the radar sensor as red, and the point cloud type for the depth sensor as green, etc. When the robot determines that there are obstacle point clouds in the first target map area, it acquires the point cloud type of the obstacle point cloud. Based on the comparison between the acquired point cloud type and the pre-set point cloud type, it identifies noisy sensors. If the acquired point cloud type matches the pre-set point cloud type, then the sensor corresponding to that pre-set point cloud type is a noisy sensor. For example, if the point cloud type is red, then the radar sensor corresponding to the red point cloud is determined to be noisy.

[0069] In the above embodiments, the robot acquires the point cloud type of the obstacle point cloud in the first target map area; and determines the noisy sensor based on the comparison result between the point cloud type and the preset point cloud type. This allows for rapid identification of noisy sensors by point cloud type, shortening the noise detection time and improving the efficiency of sensor noise detection.

[0070] In one embodiment, after S206, the method further includes: if a warning signal is received, in response to a single sensor detection operation, collecting data on the target environment through a single sensor to obtain second obstacle information; generating a second cost map based on the second obstacle information; if there are obstacle point clouds in the second target map region of the second cost map, determining that the single sensor has noise; the second target map region is the region in the second cost map that represents the target region in the target environment.

[0071] The warning signal is used to alert the sensor to noise, including audible warning signals and flashing light warning signals. The single-sensor detection operation is used to detect noise from a single sensor, and can be triggered by clicking, swiping, or dragging a trigger control. The second obstacle information is obstacle information collected through environmental perception detection using a single sensor. Since there are no obstacles in the target area, if the single sensor has no noise, the second target map area generated based on the second obstacle information will not show obstacle point clouds representing obstacles. Therefore, the presence of obstacle point clouds in the second target map area indicates that the second obstacle information collected by the single sensor contains abnormal observations, meaning the single sensor has noise.

[0072] In the above embodiments, in response to a single sensor detection operation, the target environment is collected using a single sensor to obtain second obstacle information. If obstacle point clouds are present in the second target map region of the second cost map generated based on the second obstacle information, it is determined that the single sensor is noisy. Therefore, when it is determined that there is a noisy sensor among the sensors deployed throughout the robot, noise detection can be performed on a single sensor individually to determine whether the single sensor is noisy, improving the flexibility of sensor noise detection. Furthermore, the detection operation of all sensors in the robot can be verified through the single sensor detection operation, improving the accuracy of sensor noise detection.

[0073] In one embodiment, if there is no obstacle point cloud in the second target map region of the second cost map, the system switches to another single sensor; the target environment is collected by the other single sensor to obtain third obstacle information; a third cost map is generated based on the third obstacle information; if there is obstacle point cloud in the third target map region of the third cost map, it is determined that there is noise in the other single sensor; the third target map region is the region in the third cost map that represents the target region in the target environment.

[0074] The third obstacle information is obstacle information collected through environmental perception detection using another single sensor. Since there are no obstacles in the target area, if the other single sensor is free of noise, the third target map region of the third cost map generated based on the third obstacle information will not contain obstacle point clouds representing obstacles. Therefore, the presence of obstacle point clouds in the third target map region indicates that the third obstacle information collected by the single sensor contains anomalous observations, meaning that the other single sensor has noise.

[0075] In the above embodiments, if there are no obstacle point clouds in the second target map region of the second cost map, the system switches to another single sensor. The target environment is collected using this other single sensor to obtain third obstacle information. If obstacle point clouds are present in the third target map region of the third cost map generated based on the third obstacle information, it is determined that noise exists in the other single sensor. This allows for sequential switching to each single sensor for noise detection, improving the flexibility of noise detection. Furthermore, by sequentially detecting each single sensor individually, the overall sensor detection operation can be verified, improving the accuracy of sensor noise detection.

[0076] In one embodiment, the sensor includes a radar, and after S206, the method further includes: in response to a radar detection operation, acquiring second obstacle information by means of the radar to collect information about the target environment; generating a second cost map based on the second obstacle information; determining that the radar has noise if there is an obstacle point cloud in the second target map region of the second cost map; the second target map region is the map region in the second cost map that represents the target region in the target environment.

[0077] The radar detection operation is used to detect noise on the radar, and can be triggered by clicking, sliding, or dragging a trigger control. The second obstacle information is obstacle information collected by the radar through environmental perception. Since there are no obstacles in the target area, if the radar has no noise, the second target map area generated based on the second obstacle information will not show obstacle point clouds representing obstacles. Therefore, the presence of obstacle point clouds in the second target map area indicates that the second obstacle information collected by the radar contains abnormal observations, meaning the radar has noise.

[0078] In the above embodiments, in response to the radar detection operation, the target environment is collected by the radar to obtain second obstacle information. If there are obstacle point clouds in the second target map region of the second cost map generated based on the second obstacle information, it is determined that the radar has noise. Therefore, when it is determined that there are noisy sensors among the sensors deployed in the robot, noise detection can be performed on the radar separately to determine whether the radar is a noisy sensor, improving the flexibility of sensor noise detection. Furthermore, the overall sensor detection operation can be verified by performing radar detection operations separately, improving the accuracy of sensor noise detection.

[0079] In one embodiment, the sensor includes a depth sensor; after S206, the method further includes: in response to a depth sensor detection operation, acquiring third obstacle information by means of the depth sensor to collect information about the target environment; generating a third cost map based on the third obstacle information; if there are obstacle point clouds in the third map region of the third cost map, determining that there is noise in the depth sensor; the third map region is a map region in the third cost map that represents the target region in the target environment.

[0080] The depth sensor detection operation is used to detect noise in the depth sensor, and can be triggered by clicking, swiping, or dragging a control. The third obstacle information is obstacle information collected by the depth sensor through environmental perception. Since there are no obstacles in the target area, if the depth sensor has no noise, the third target map region of the third cost map generated based on the third obstacle information will not contain obstacle point clouds representing obstacles. Therefore, the presence of obstacle point clouds in the third target map region indicates that the third obstacle information collected by the depth sensor contains abnormal observations, meaning the depth sensor has noise.

[0081] In the above embodiments, in response to the depth sensor detection operation, the target environment is collected by the depth sensor to obtain third obstacle information. If there are obstacle point clouds in the third target map region of the third cost map generated based on the third obstacle information, it is determined that the depth sensor has noise. Therefore, when it is determined that there is a noisy sensor among the sensors deployed in the robot, noise detection can be performed on the depth sensor separately to determine whether the depth sensor is a noisy sensor, improving the flexibility of sensor noise detection. Furthermore, the detection operation of the entire robot's sensors can be verified by performing the depth sensor detection operation separately, improving the accuracy of sensor noise detection.

[0082] In one embodiment, after S204, the method further includes: displaying a first cost map on the sensor noise detection interface; S206 specifically includes: if there are obstacle point clouds in the first target map area displayed on the sensor noise detection interface, determining that there are noisy sensors among the sensors of the robot as a whole.

[0083] The sensor noise detection interface is used for sensor noise detection, including sensor detection operation trigger controls and a cost map display area. The sensor detection operation trigger controls include overall robot sensor detection operation trigger controls as well as individual sensor detection operation trigger controls such as radar detection operation trigger controls and depth sensor detection operation trigger controls. The robot displays the obstacle point cloud in the first cost map. Since there are no obstacles in the target area of ​​the target environment, if none of the robot's sensors are noisy, the obstacle point cloud will not be displayed in the first target map area of ​​the sensor noise detection interface. Therefore, when the obstacle point cloud is displayed in the first target map area, it can be determined that there are noisy sensors among the robot's sensors.

[0084] In the above embodiments, the robot displays a first cost map on the sensor noise detection interface. If obstacle point clouds are displayed in the first target map area shown on the sensor noise detection interface, it is determined that there are noisy sensors among the robot's sensors. The robot displays the first cost map in a visual manner, which allows for convenient and quick determination of whether there are obstacle point clouds in the first target map area, thus improving the efficiency of sensor noise detection.

[0085] In one embodiment, S206 is followed by: if there is no obstacle point cloud in the first target map region, determine that there is no noise in the sensors of the robot as a whole.

[0086] Since there are no obstacles in the target area, if there is no obstacle point cloud in the first target map area, it means that the first obstacle information collected by the sensor does not contain abnormal observations, that is, there is no noise in the sensors of the robot as a whole.

[0087] Traditional techniques sequentially test each sensor individually, only determining the absence of noise in the robot's sensors after all tests are completed. In the above embodiment, if no obstacle point cloud exists in the first target map region, it is determined that the robot's sensors are noise-free. This eliminates the need for sequential testing of each sensor, allowing for a rapid determination of sensor noise and improving the efficiency of overall sensor testing.

[0088] In one embodiment, before S202, the method further includes: opening a noise detection application in response to a detection program startup operation; and displaying a sensor noise detection interface through the noise detection application. S202 specifically includes: in response to a whole-machine sensor detection operation triggered by the sensor noise detection interface, collecting data from the target environment using sensors deployed throughout the robot to obtain first obstacle information.

[0089] In one embodiment, such as Figure 5 As shown, the robot moves to the front of the target area in the target environment, where there are no obstacles. In response to the detection program initiation operation, the noise detection application is opened, and the sensor noise detection interface is displayed. Figure 6As shown, the sensor noise detection interface includes whole-machine sensor detection trigger controls, radar detection trigger controls, depth sensor 1 (detecting for suspended obstacles) detection trigger controls, depth sensor 2 (detecting for low obstacles) detection trigger controls, sound alarm activation controls, and a first cost map display area. In response to the sound alarm activation operation triggered by the sound alarm activation control, the sound alarm function is activated. In response to the trigger operation of the whole-machine sensor detection trigger controls, noise detection is performed on the sensors deployed throughout the robot. Noise detection on the sensors deployed throughout the robot includes: collecting data from the target environment using the sensors deployed throughout the robot to obtain first obstacle information; generating a first cost map based on the first obstacle information; if there are obstacle point clouds in the first target map area of ​​the first cost map, it is determined that there are noisy sensors among the robot's sensors. The first target map area is the map area in the first cost map that represents the target area without obstacles in the target environment. If it is determined that there are noisy sensors among the robot's sensors, a sound alarm is triggered. If there are no obstacle point clouds in the first target map area of ​​the first cost map, it is determined that there is no noise among the robot's sensors. If the robot receives a radar detection command triggered by a radar detection trigger control, it performs noise detection on the radar. Radar noise detection includes: collecting data about the target environment using the radar to obtain second obstacle information; generating a second cost map based on the second obstacle information; and if obstacle point clouds are present in the second target map region of the second cost map, determining that noise exists in the radar and issuing an audible alarm. The second target map region is the map region in the second cost map that represents the target area in the target environment. If the robot receives a detection command triggered by a depth sensor 1 detection trigger control, it performs noise detection on depth sensor 1. Depth sensor 1 noise detection includes: collecting data about the target environment using depth sensor 1 to obtain third obstacle information; generating a third cost map based on the third obstacle information; and if obstacle point clouds are present in the third target map region of the third cost map, determining that noise exists in depth sensor 1 and issuing an audible alarm. The third target map region is the map region in the third cost map that represents the target area in the target environment. If the robot receives a detection command triggered by a depth sensor 2 detection trigger control, it performs noise detection on depth sensor 2. Noise detection for depth sensor 2 includes: acquiring fourth obstacle information by collecting data from the target environment using depth sensor 2; generating a fourth cost map based on the fourth obstacle information; and determining that there is obstacle point cloud in the fourth target map region of the fourth cost map and issuing an audible alarm if noise is present in depth sensor 2. The fourth target map region is the map region in the third cost map that represents the target area in the target environment.

[0090] In one embodiment, such as Figure 7As shown, the sensor noise detection method includes the following steps:

[0091] S702, Open the noise detection application; The noise detection application displays the sensor noise detection interface.

[0092] S704, in response to the whole-machine sensor detection operation triggered by the sensor noise detection interface, collects the target environment through the sensors deployed throughout the robot to obtain the first obstacle information.

[0093] S706, Generate and display a first cost map based on the first obstacle information.

[0094] S708, if there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region.

[0095] S710, if there are no obstacle point clouds in the first target map area, it is determined that there is no noise in the sensors of the robot as a whole.

[0096] S712, if a warning signal is received, responds to the single sensor detection operation, collects the target environment through the single sensor, obtains the second obstacle information, and generates a second cost map based on the second obstacle information;

[0097] S714, if there are obstacle point clouds in the second target map region of the second cost map, it is determined that there is noise in the single sensor; the second target map region is the region in the second cost map that represents the target region in the target environment.

[0098] S716, if there is no obstacle point cloud in the second target map area of ​​the second cost map, switch to another single sensor.

[0099] S718 collects information about the target environment through another single sensor, obtains information about the third obstacle, and generates a third cost map based on the information about the third obstacle.

[0100] S720, if there are obstacle point clouds in the third target map region of the third cost map, determine that there is noise in another single sensor; the third target map region is the region in the third cost map that represents the target region in the target environment.

[0101] For details on S702 to S720 above, please refer to the specific implementation process described above.

[0102] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0103] Based on the same inventive concept, this application also provides a sensor noise detection device for implementing the sensor noise detection method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more sensor noise detection device embodiments provided below can be found in the limitations of the sensor noise detection method described above, and will not be repeated here.

[0104] In one embodiment, such as Figure 8 As shown, a sensor noise detection device is provided, comprising: a data acquisition module 802, a generation module 804, and a determination module 806, wherein:

[0105] The data acquisition module 802 is used to collect data on the target environment through sensors deployed throughout the robot to obtain information about the first obstacle.

[0106] Generation module 804 is used to generate a first cost map based on the first obstacle information;

[0107] The determination module 806 is used to determine that if there is an obstacle point cloud in the first target map region of the first cost map, there is a noisy sensor among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region.

[0108] In the above embodiments, in response to the overall robot sensor detection operation, the sensors deployed on the robot collect data on the target environment to obtain first obstacle information; a first cost map is generated based on the first obstacle information; if there is an obstacle point cloud in the first target map region of the first cost map, it is determined that there is a noisy sensor among the robot's sensors; the first target map region is the map region in the first cost map that represents the target area where there are no obstacles in the target environment. Since there are no obstacles in the target area, if none of the robot's sensors are noisy, then no obstacle point cloud representing obstacles will appear in the first target map region of the first cost map generated based on the first obstacle information. Therefore, when there is an obstacle point cloud in the first target map region, it indicates that the first obstacle information collected by the sensors contains abnormal observations, that is, there is a noisy sensor among the robot's sensors. Thus, it is not necessary to detect each sensor sequentially to quickly determine whether the overall robot's sensors are noisy, improving the efficiency of detecting the robot's sensors.

[0109] In one embodiment, such as Figure 9 As shown, the device also includes:

[0110] The acquisition module 808 is used to acquire the point cloud type of the obstacle point cloud in the first target map area;

[0111] The determination module 806 is also used to determine noisy sensors based on the comparison results between the point cloud type and the preset point cloud type.

[0112] In one embodiment, the apparatus further includes:

[0113] The acquisition module 802 is also used to, in response to a single sensor detection operation, acquire information about the target environment through a single sensor to obtain information about the second obstacle if a warning signal is received;

[0114] The generation module 804 is also used to generate a second cost map based on the second obstacle information;

[0115] The determination module 806 is further configured to determine that a single sensor has noise if there is an obstacle point cloud in the second target map region of the second cost map; the second target map region is the region in the second cost map that represents the target region in the target environment.

[0116] In one embodiment, the apparatus further includes:

[0117] The switching module 810 is used to switch to another single sensor if there is no obstacle point cloud in the second target map area of ​​the second cost map.

[0118] The acquisition module 802 is also used to acquire information about the target environment through another single sensor to obtain information about a third obstacle;

[0119] The generation module 804 is also used to generate a third cost map based on the third obstacle information;

[0120] The determination module 806 is also used to determine that there is noise in another single sensor if there is an obstacle point cloud in the third target map region of the third cost map; the third target map region is the region in the third cost map that represents the target region in the target environment.

[0121] In one embodiment, the apparatus further includes:

[0122] Display module 812 is used to display the first cost map on the sensor noise detection interface;

[0123] The determination module 806 is further configured to, if there are obstacle point clouds in the first target map region of the first cost map, determine whether any noisy sensors exist among the robot's sensors, including:

[0124] The determination module 806 is also used to determine that if there are obstacle point clouds in the first target map area displayed by the sensor noise detection interface, there are noisy sensors among the sensors of the robot as a whole.

[0125] In one embodiment, the apparatus further includes:

[0126] The determination module 806 is also used to determine that there is no noise in the sensors of the robot if there is no obstacle point cloud in the first target map area.

[0127] Each module in the aforementioned sensor noise detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the robot's processor in hardware form or independent of it, or stored in the robot's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0128] In one embodiment, a robot is provided whose internal structure diagram can be as follows: Figure 10As shown, the robot includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The robot's processor provides computational and control capabilities. The robot's memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The robot's input / output interface is used for exchanging information between the processor and external devices. The robot's communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a sensor noise detection method. The robot's display unit is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The robot's input device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad set on the robot's shell, or an external keyboard, touchpad, or mouse, etc.

[0129] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the robot to which the present application is applied. A specific robot may include more or fewer parts than shown in the figure, or combine certain parts, or have different part arrangements.

[0130] In one embodiment, a robot is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps in the above method embodiments.

[0131] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0132] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0133] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0134] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0135] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A sensor noise detection method, characterized in that, The method includes: The robot collects information about the target environment using sensors deployed throughout the robot, thus obtaining information about the first obstacle. A first cost map is generated based on the first obstacle information; If there are obstacle point clouds in the first target map region of the first cost map, it is determined that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region; Obtain the point cloud type of the obstacle point cloud in the first target map area; wherein, the robot pre-sets the point cloud type of the obstacle point cloud corresponding to each of the sensors; The noisy sensor is determined based on the comparison result between the point cloud type and the preset point cloud type.

2. The method according to claim 1, characterized in that, After determining that there are noisy sensors among the sensors of the robot, the method further includes: If a warning signal is received, in response to a single sensor detection operation, the target environment is collected through the single sensor to obtain second obstacle information; A second cost map is generated based on the second obstacle information; If there are obstacle point clouds in the second target map region of the second cost map, it is determined that the single sensor has noise; the second target map region is the region in the second cost map that represents the target region in the target environment.

3. The method according to claim 2, characterized in that, The method further includes: If there are no obstacle point clouds in the second target map area of ​​the second cost map, switch to another single sensor; The target environment is collected using the other single sensor to obtain information about the third obstacle; A third cost map is generated based on the third obstacle information; If there are obstacle point clouds in the third target map region of the third cost map, it is determined that the other single sensor has noise; the third target map region is the region in the third cost map that represents the target region in the target environment.

4. The method according to claim 1, characterized in that, After generating the first cost map based on the first obstacle information, the method further includes: The first cost map is displayed on the sensor noise detection interface; If there are obstacle point clouds in the first target map region of the first cost map, determining that there are noisy sensors among the sensors in the robot includes: If there are obstacle point clouds in the first target map area displayed by the sensor noise detection interface, it is determined that there are noisy sensors among the sensors in the robot.

5. The method according to claim 1, characterized in that, The method further includes: If there are no obstacle point clouds in the first target map area, it is determined that there is no noise in the sensors of the robot as a whole.

6. A sensor noise detection device, characterized in that, The device includes: The data acquisition module is used to collect data from the target environment through sensors deployed throughout the robot to obtain information about the first obstacle. The generation module is used to generate a first cost map based on the first obstacle information; The determination module is used to determine, if there are obstacle point clouds in the first target map region of the first cost map, that there are noisy sensors among the sensors of the robot; the first target map region is the region in the first cost map that represents the target region in the target environment; there are no obstacles in the target region; The acquisition module is used to acquire the point cloud type of the obstacle point cloud in the first target map area; wherein, the robot pre-sets the point cloud type of the obstacle point cloud corresponding to each of the sensors; The determining module is further configured to determine the noisy sensor based on the comparison result between the point cloud type and a preset point cloud type.

7. The apparatus according to claim 6, characterized in that, The device further includes: The acquisition module is also used to, in response to a single sensor detection operation, acquire information about the target environment through the single sensor if a warning signal is received, to obtain second obstacle information; The generation module is further configured to generate a second cost map based on the second obstacle information; The determining module is further configured to determine that the single sensor has noise if there is an obstacle point cloud in the second target map region of the second cost map; the second target map region is the region in the second cost map that represents the target region in the target environment.

8. A robot comprising a memory and a processor, the memory storing computer-readable instructions executable on the processor, characterized in that, When the processor executes the computer-readable instructions, it performs the following steps: The robot collects information about the target environment using sensors deployed throughout the robot, thus obtaining information about the first obstacle. A first cost map is generated based on the first obstacle information; If there are obstacle point clouds in the first target map area of ​​the first cost map, it is determined that there are noisy sensors among the sensors of the robot as a whole; The first target map region is the region in the first cost map that represents the target area in the target environment; there are no obstacles in the target region; Obtain the point cloud type of the obstacle point cloud in the first target map area; wherein, the robot pre-sets the point cloud type of the obstacle point cloud corresponding to each of the sensors; The noisy sensor is determined based on the comparison result between the point cloud type and the preset point cloud type.

9. The robot according to claim 8, characterized in that, When the processor executes the computer-readable instructions, it also performs the following steps: If a warning signal is received, in response to a single sensor detection operation, the target environment is collected through the single sensor to obtain second obstacle information; A second cost map is generated based on the second obstacle information; If there are obstacle point clouds in the second target map area of ​​the second cost map, it is determined that the single sensor has noise; The second target map region is the region in the second cost map that represents the target region in the target environment.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images