Robot collision avoidance methods, self-moving devices and computer-readable storage media

Abstract

This application provides a robot collision avoidance method, a self-moving device, and a computer-readable storage medium. The robot collision avoidance method includes: acquiring obstacle distance feedback values ​​from a target ultrasonic sensor installed on the robot; determining target calibration parameters for the obstacle distance feedback values ​​based on preset reference distance ranges associated with various calibration parameters; calibrating the obstacle distance feedback values ​​according to the target calibration parameters to obtain obstacle distance calibration values ​​for the target ultrasonic sensor; and controlling the robot's movement based on the obstacle distance calibration values. This application can improve the recognition accuracy of obstacles, especially transparent obstacles, to a certain extent, reduce the probability of robot collisions, and improve robot operational safety.

Description

Technical Field

[0001] This application relates to the field of robotics technology, specifically to a robot collision avoidance method, a self-moving device, and a computer-readable storage medium. Background Technology

[0002] With the continuous development of robotics technology, autonomous navigation and obstacle avoidance systems are increasingly widely used in fields such as unmanned vehicles and drones. To meet the needs of autonomous navigation and obstacle avoidance for robots, related technologies employ lidar reflection detection of obstacles. However, lidar cannot detect transparent objects with light-transmitting properties, such as glass. Therefore, how to achieve glass collision avoidance has become an important research problem for autonomous navigation and obstacle avoidance in robots.

[0003] In the actual research and development process, the inventors of this application discovered that there are two main methods for glass anti-collision in related technologies. One method uses physical structures such as anti-collision strips. However, physical anti-collision mechanisms can only react after contact with the glass, which poses a risk of damage to the object due to untimely reaction. The other method uses sensors such as ultrasonic sensors for detection. However, due to the influence of environmental humidity and other factors, the propagation of waves has a certain diffusion angle, making it difficult to accurately detect the specific location of obstacles. Therefore, the probability of the robot colliding with obstacles is relatively high. Summary of the Invention

[0004] This application provides a robot collision avoidance method, a self-moving device, and a computer-readable storage medium, which can improve the recognition accuracy of obstacles, especially transparent obstacles, to a certain extent, reduce the probability of robot collisions with obstacles, and improve the safety of robot operation.

[0005] In a first aspect, this application provides a robot collision avoidance method, the method comprising:

[0006] Obtain obstacle distance feedback values ​​from the target ultrasonic sensors installed on the robot;

[0007] Based on the preset reference distance range associated with each calibration parameter, the target calibration parameters for the obstacle distance feedback value are determined;

[0008] The obstacle distance feedback value is calibrated according to the target calibration parameters to obtain the obstacle distance calibration value of the target ultrasonic sensor;

[0009] The robot's movement is controlled based on the obstacle distance calibration value.

[0010] Secondly, this application also provides a self-moving device, which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes any of the robot collision avoidance methods provided in this application when it calls the computer program in the memory.

[0011] Thirdly, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the robot collision avoidance method.

[0012] In this application, firstly, different calibration parameters are set for different reference distance ranges; target calibration parameters for the obstacle distance feedback value of the target ultrasonic sensor are determined according to the reference distance range associated with each preset calibration parameter; the obstacle distance feedback value is calibrated according to the target calibration parameters to obtain the obstacle distance calibration value of the target ultrasonic sensor. Different calibration parameters can be used to calibrate different obstacle distance calibration values, thus allowing for calibration based on environmental interference at different distances. This avoids the problem of low data accuracy caused by increased environmental interference with increasing distance, improving the calibration accuracy of obstacle distance to a certain extent, making the obstacle distance calibration value closer to the actual distance of the obstacle, thereby improving the recognition accuracy of obstacle identification using ultrasonic sensors and reducing robot collisions. Secondly, by utilizing ultrasonic sensors, transparent obstacles such as glass can be effectively identified, increasing the probability of identifying transparent obstacles such as glass during robot navigation, thereby reducing collisions between the robot and transparent obstacles such as glass. Therefore, the embodiments of this application can improve the recognition accuracy of obstacles, especially transparent obstacles, to a certain extent, reduce the probability of robot collisions, and improve robot operation safety. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic block diagram of the structure of a self-moving device provided in an embodiment of this application;

[0015] Figure 2 This is a schematic flowchart of a robot collision avoidance method provided in an embodiment of this application;

[0016] Figure 3 This is a schematic diagram illustrating the deployment location of the ultrasonic sensor in the embodiments of this application;

[0017] Figure 4 This is a schematic flowchart of one embodiment of obstacle marking in this application;

[0018] Figure 5This is a schematic flowchart of an embodiment of obstacle marking using obstacle identification information from an ultrasonic sensor in this application.

[0019] Figure 6 This is a schematic diagram of one embodiment of the robot collision avoidance process provided in this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0022] In the description of the embodiments of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0023] To enable any person skilled in the art to implement and use this application, the following description is provided. In this description, details are set forth for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be implemented without using these specific details. In other instances, well-known processes will not be described in detail to avoid obscuring the description of the embodiments of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in the embodiments of this application.

[0024] This application provides a robot collision avoidance method, a self-moving device, and a computer-readable storage medium. The self-moving device can be a cleaning robot, a food delivery robot, etc.

[0025] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0026] Figure 1This is a schematic block diagram of the structure of a self-moving device provided in an embodiment of this application.

[0027] like Figure 1 As shown, the self-moving device 100 includes a processor 101 and a memory 102, which are connected via a bus 103, such as a PCIe (Peripheral Component Interconnect Express) bus.

[0028] Specifically, processor 101 provides computing and control capabilities to support the operation of the entire self-moving device 100. Processor 101 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0029] Specifically, the memory 102 can be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a portable hard drive, etc.

[0030] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the embodiments of this application, and does not constitute a limitation on the self-moving device to which the embodiments of this application are applied. A specific self-moving device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0031] The processor 101 is configured to run a computer program stored in the memory 102, and implement any of the robot collision avoidance methods provided in this application embodiment when executing the computer program. For example, the processor 101 is configured to run a computer program stored in the memory 102, and can implement the following steps when executing the computer program:

[0032] Obtain obstacle distance feedback values ​​from target ultrasonic sensors installed on the robot; determine target calibration parameters for the obstacle distance feedback values ​​based on preset reference distance ranges associated with each calibration parameter; calibrate the obstacle distance feedback values ​​according to the target calibration parameters to obtain obstacle distance calibration values ​​for the target ultrasonic sensors; control the robot's movement based on the obstacle distance calibration values.

[0033] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, it may perform the following steps:

[0034] Based on the obstacle distance calibration value, a preset rotation distance threshold and a preset stop distance threshold are used to determine the robot's execution action; based on the execution action, motion control commands for the robot are generated to control the robot's movement process.

[0035] In some embodiments, the robot is equipped with a plurality of ultrasonic sensors, and the processor 101 is used to run a computer program stored in the memory 102, and when executing the computer program, it can perform the following steps:

[0036] Obtain the first obstacle detection result of each ultrasonic sensor installed on the robot; use each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected as the target ultrasonic sensor.

[0037] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, it may perform the following steps:

[0038] Each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected is used as a preliminary screening ultrasonic sensor; the second obstacle detection result of the robot's laser-type sensor at the detection position corresponding to the preliminary screening ultrasonic sensor is obtained; if the second obstacle detection result indicates that no obstacle has been detected, the preliminary screening ultrasonic sensor is used as the target ultrasonic sensor.

[0039] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, it may perform the following steps:

[0040] Based on the fan-shaped detection area of ​​the target ultrasonic sensor and the obstacle distance calibration value, the position of the newly detected obstacle by the target ultrasonic sensor is determined; based on the position of the newly detected obstacle, the newly detected obstacle is marked on the obstacle map of the robot to obtain an updated obstacle map; based on the updated obstacle map, the robot is controlled to avoid obstacles.

[0041] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, it may perform the following steps:

[0042] Obtain the calibration distance threshold of the obstacle distance feedback value; if the obstacle distance feedback value is less than the calibration distance threshold, mark the newly detected obstacle on the robot's obstacle map based on the position of the newly detected obstacle to obtain an updated obstacle map.

[0043] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, it may perform the following steps:

[0044] The robot's current moving speed is obtained; based on the current moving speed, a calibration distance threshold for the obstacle distance feedback value is determined, wherein the current moving speed is positively correlated with the calibration distance threshold.

[0045] In some embodiments, the processor 101 is configured to run a computer program stored in the memory 102, and when executing the computer program, it may perform the following steps:

[0046] Obtain the cumulative marking duration of the newly detected obstacle; if the cumulative marking duration is greater than a preset marking duration threshold, then delete the newly detected obstacle from the obstacle map.

[0047] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the self-moving device described above can be referred to the corresponding process in the following robot collision avoidance method embodiments, and will not be repeated here.

[0048] The following will be based on Figure 1 Taking the self-moving device shown as the execution subject of the robot collision avoidance method as an example, the robot collision avoidance method provided in this application embodiment will be described in detail. For simplicity and ease of description, the execution subject will be omitted in subsequent method embodiments. It should be noted that... Figure 1 The scenarios described are only used to explain the robot collision avoidance method provided in the embodiments of this application, but do not constitute a limitation on the application scenarios of the robot collision avoidance method provided in the embodiments of this application.

[0049] Please see Figure 2 , Figure 2 This is a flowchart illustrating a robot collision avoidance method provided in an embodiment of this application. The robot collision avoidance method includes steps 201-204, wherein:

[0050] 201. Obtain the obstacle distance feedback value from the target ultrasonic sensor installed on the robot.

[0051] Here, obstacle distance refers to the distance between the robot and the obstacle.

[0052] Among them, the obstacle distance feedback value refers to the obstacle distance detected and fed back by the ultrasonic sensor (i.e., the distance between the robot and the obstacle).

[0053] To improve obstacle detection accuracy and avoid the problem of robots struggling to accurately detect the specific location of transparent objects such as glass, this embodiment equips the robot with ultrasonic sensors. The location and number of ultrasonic sensors can be set according to the actual business scenario requirements. For example, ... Figure 3 As shown in this embodiment, in order to improve the comprehensiveness of obstacle detection, an ultrasonic sensor is deployed at the center, left, right, front left, and front right positions of the robot chassis.

[0054] For example, during the robot's movement, ultrasonic data can be collected by a target ultrasonic sensor deployed on the robot chassis. In step 201, the ultrasonic data collected by the target ultrasonic sensor can be obtained, thereby obtaining the obstacle distance feedback value of the robot's target ultrasonic sensor.

[0055] In step 201, there are multiple ways to obtain the obstacle distance feedback value, including, for example:

[0056] (1) An ultrasonic sensor is installed on the robot. At this time, the target ultrasonic sensor refers to the ultrasonic sensor installed on the robot. In step 201, the ultrasonic data collected by the target ultrasonic sensor can be obtained, thereby obtaining the obstacle distance feedback value of the target ultrasonic sensor of the robot.

[0057] (2) Multiple ultrasonic sensors are installed on the robot. At this time, the target ultrasonic sensor is the ultrasonic sensor that detects obstacles. It can be determined first whether there is a target ultrasonic sensor among the multiple ultrasonic sensors installed on the robot. When there is a target ultrasonic sensor among the multiple ultrasonic sensors installed on the robot, in step 201, the ultrasonic data collected by the target ultrasonic sensor can be obtained, thereby obtaining the obstacle distance feedback value of the robot's target ultrasonic sensor.

[0058] In some embodiments, the ultrasonic sensors mounted on the robot include at least two of the following: a first ultrasonic sensor located at the center of the front of the robot chassis; a second ultrasonic sensor located at the left side of the robot chassis; a third ultrasonic sensor located at the right side of the robot chassis; a fourth ultrasonic sensor located at the front left of the robot chassis; and a fifth ultrasonic sensor located at the front right of the robot chassis.

[0059] In some embodiments, in order to enable the robot to operate flexibly and avoid collisions with transparent obstacles such as glass in complex environments and improve the comprehensiveness of obstacle recognition, the ultrasonic sensors installed on the robot include a first ultrasonic sensor located at the center of the front of the robot chassis, a second ultrasonic sensor located at the left side of the robot chassis, a third ultrasonic sensor located at the right side of the robot chassis, a fourth ultrasonic sensor located at the front left of the robot chassis, and a fifth ultrasonic sensor located at the front right of the robot chassis.

[0060] For example, the target ultrasonic sensor can be determined by referring to the following steps A1 to A2:

[0061] A1. Obtain the first obstacle detection result of each ultrasonic sensor installed on the robot.

[0062] The first obstacle detection result refers to the obstacle detection result of the ultrasonic sensor, which indicates whether the ultrasonic sensor has detected an obstacle.

[0063] A2. Each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected is designated as the target ultrasonic sensor.

[0064] There are multiple ways to implement step A2, including, for example, the following methods ① and ②:

[0065] ① Each ultrasonic sensor that detects an obstacle is directly used as the target ultrasonic sensor.

[0066] For example, taking a robot equipped with a first, second, third, fourth, and fifth ultrasonic sensor as an example, in steps A1 to A2, the first obstacle detection result of the first ultrasonic sensor is obtained; if the first obstacle detection result of the first ultrasonic sensor indicates that an obstacle has been detected, then the first ultrasonic sensor is designated as the target ultrasonic sensor; if the first obstacle detection result of the first ultrasonic sensor indicates that no obstacle has been detected, no further processing is performed. This process is repeated to determine whether the second, third, fourth, and fifth ultrasonic sensors are designated as target ultrasonic sensors.

[0067] ② Please refer to Figure 4 To improve obstacle marking accuracy, obstacle detection results from ultrasonic sensors and laser sensors are integrated. On one hand, considering that ultrasonic sensors can identify transparent obstacles such as glass, but have low accuracy and cannot confirm the specific location of obstacles, ultrasonic sensors are used as supplementary sensors. On the other hand, taking advantage of the fact that ultrasonic sensors can identify transparent obstacles such as glass, but laser sensors cannot, non-transparent obstacles are excluded. Therefore, when both ultrasonic and laser sensors detect an obstacle, the obstacle identification information from the laser sensor is used for obstacle marking; when the ultrasonic sensor detects an obstacle, but the laser sensor does not, the obstacle identification information from the ultrasonic sensor is used for obstacle marking. Therefore, step A2 may specifically include: using each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected as a preliminary screening ultrasonic sensor; obtaining the second obstacle detection result of the robot's laser sensor at the detection position corresponding to the preliminary screening ultrasonic sensor; if the second obstacle detection result indicates that no obstacle has been detected, then the preliminary screening ultrasonic sensor is used as the target ultrasonic sensor. Therefore, by using the detection data from the target ultrasonic sensor (such as obstacle distance feedback value), non-transparent objects can be filtered out while transparent objects are selected, preventing the robot from colliding with transparent obstacles, reducing the robot's obstacle collision risk, and improving the robot's driving safety.

[0068] The second obstacle detection result refers to the obstacle detection result of the laser sensor, which is used to indicate whether the laser sensor has detected an obstacle.

[0069] Among them, laser sensors can include RGBD (Red-Green-Blue Depth) cameras and laser detection devices. RGBD cameras are responsible for low-lying objects, while laser detection devices are responsible for distant objects.

[0070] For example, taking a robot equipped with a first, second, third, fourth, and fifth ultrasonic sensors as an example, in steps A1-A2, the first obstacle detection result of the first ultrasonic sensor and the second obstacle detection result of the robot's laser-type sensor at the detection position corresponding to the first ultrasonic sensor are obtained. If the first obstacle detection result of the first ultrasonic sensor indicates that an obstacle has been detected, and the second obstacle detection result indicates that no obstacle has been detected, then the first ultrasonic sensor is designated as the target ultrasonic sensor, and obstacle identification information from the first ultrasonic sensor is used for obstacle marking in steps 501-502. If the first obstacle detection result of the first ultrasonic sensor indicates that no obstacle has been detected, and the second obstacle detection result indicates that an obstacle has been detected, then obstacle identification information from the laser-type sensor is used for obstacle marking in steps 501-502. If both the first and second obstacle detection results of the first ultrasonic sensor indicate that no obstacle has been detected, no further processing is performed. This process is repeated to determine whether the second, third, fourth, and fifth ultrasonic sensors are designated as target ultrasonic sensors.

[0071] For example, such as Figure 4 As shown, when marking obstacles by fusing the obstacle detection results of ultrasonic sensors and laser sensors, the marking method is as follows: ① If the second obstacle detection result obtained in step 403 is that no obstacle was detected, then the obstacle detected by the ultrasonic sensor is a transparent obstacle such as glass. If it is a transparent obstacle such as glass, the obstacle marking process can proceed as follows: steps 401 to 409. ② If the second obstacle detection result obtained in step 403 is that an obstacle was detected, then the obstacle detected by the ultrasonic sensor is a non-transparent obstacle. If it is a non-transparent obstacle, the obstacle marking process can proceed as follows: steps 401 to 403 and steps 410 to 411.

[0072] 401. Obtain the first obstacle detection result of each ultrasonic sensor installed on the robot.

[0073] The implementation of step 401 is similar to that of step A1, and will not be repeated here.

[0074] 402. Each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected is used as a preliminary screening ultrasonic sensor.

[0075] 403. Obtain the second obstacle detection result of the robot's laser sensor at the detection position corresponding to the initial screening ultrasonic sensor.

[0076] 404. If the second obstacle detection result is that no obstacle is detected, then the initial screening ultrasonic sensor shall be used as the target ultrasonic sensor.

[0077] The implementation of steps 402 to 404 is similar to method ② in step A2, and will not be repeated here.

[0078] If the second obstacle detection result is that no obstacle is detected, then the obstacle identification information of the ultrasonic sensor is used to mark the obstacle and generate motion control commands.

[0079] 405. Obtain the obstacle distance feedback value from the target ultrasonic sensor installed on the robot.

[0080] 406. Determine the target calibration parameters for the obstacle distance feedback value based on the preset reference distance range associated with each calibration parameter.

[0081] 407. The obstacle distance feedback value is calibrated according to the target calibration parameters to obtain the obstacle distance calibration value of the target ultrasonic sensor.

[0082] The implementation of steps 405 to 407 is similar to that of steps 201 to 203, and will not be described again here.

[0083] 408. Based on the fan-shaped detection area of ​​the target ultrasonic sensor and the obstacle distance calibration value, determine the position of the new obstacle detected by the target ultrasonic sensor.

[0084] 409. Based on the location of the newly detected obstacle, mark the newly detected obstacle on the robot's obstacle map to obtain an updated obstacle map.

[0085] The implementation of steps 408 to 409 is similar to that of steps 501 to 502, and will not be described again here.

[0086] 410. If the second obstacle detection result is that an obstacle has been detected, then the location of the newly added obstacle detected by the robot's laser sensor is obtained.

[0087] At this point, if the second obstacle detection result indicates that an obstacle has been detected, the obstacle identification information from the laser sensor is used to mark the obstacle and generate motion control commands.

[0088] 411. Based on the location of the newly added obstacle, mark the newly added obstacle on the obstacle map of the robot to obtain an updated obstacle map.

[0089] Therefore, obstacle detection results from ultrasonic sensors and laser sensors can be integrated for obstacle marking. Ultrasonic sensors can be used to effectively identify and mark transparent obstacles such as glass. When both ultrasonic sensors and laser sensors detect obstacles, the obstacle identification information from laser sensors can be used for obstacle marking to improve the accuracy of obstacle location marking.

[0090] 202. Determine the target calibration parameters for the obstacle distance feedback value based on the preset reference distance range associated with each calibration parameter.

[0091] The calibration parameters are used to correct the obstacle distance feedback value.

[0092] For example, multiple reference distance ranges can be defined, each corresponding to a calibration parameter. The reference distance range into which the obstacle distance feedback value falls is used as the target reference distance range for the obstacle distance feedback value. The calibration parameter associated with the target reference distance range is used as the target calibration parameter for the obstacle distance feedback value. For example, five reference distance ranges are preset: [0,A), [A,B), [B,C), [C,D), [D,E). The corresponding calibration parameters for the reference distance ranges [0,A), [A,B), [B,C), [C,D), [D,E) are a, b, c, d, and e, respectively. Assuming the obstacle distance feedback value of the ultrasonic sensor is in [0,A), then the target calibration parameter for the obstacle distance feedback value is a.

[0093] In some embodiments, in order to improve the calibration accuracy of obstacle distance, at least three reference distance ranges are divided according to the lower limit boundary value K1 and the upper limit boundary value K2 of the preset error range, including the reference distance range of the first calibration parameter (e.g., the reference distance range of the first calibration parameter is [0, K1)), the reference distance range of the second calibration parameter (e.g., the reference distance range of the second calibration parameter is [K1, K2)), and the reference distance range of the third calibration parameter (e.g., the reference distance range of the third calibration parameter is [K2, the sensing boundary of the ultrasonic sensor)).

[0094] The preset error range is the range of values ​​for the target obstacle distance feedback value. The target obstacle distance feedback value refers to the obstacle distance feedback value whose difference from the true obstacle distance is less than the error distance of the laser sensor.

[0095] It is evident that the first boundary value (i.e., the upper boundary value of the reference distance range associated with the first calibration parameter, and also the lower boundary value of the reference distance range associated with the second calibration parameter) is the same as the lower boundary value of the preset error range, and the second boundary value (i.e., the upper boundary value of the reference distance range associated with the second calibration parameter, and also the lower boundary value of the reference distance range associated with the third calibration parameter) is the same as the upper boundary value of the preset error range. Therefore, by using the lower boundary value K1 and the upper boundary value K2 of the preset error range to divide at least three reference distance ranges: the reference distance range of the first calibration parameter, the reference distance range of the second calibration parameter, and the reference distance range of the third calibration parameter, such that when the obstacle distance feedback value is within the reference distance range associated with the second calibration parameter (e.g., [K1, K2)), the difference between the obstacle distance feedback value and the true obstacle distance value is less than the error distance of the laser sensor, thereby achieving the same accuracy of the ultrasonic sensor's detection data calibration value as that of the laser sensor. For example, when the error of a laser sensor is within 1 cm, the true distance to an obstacle and the feedback distance of the obstacle can be measured simultaneously in advance. The feedback distance of the obstacle with a difference of less than 1 cm from the true distance to the obstacle can be used as the target obstacle distance feedback value. This gives the range of the target obstacle distance feedback value (i.e., the preset error range). Then, the lower limit boundary value K1 and the upper limit boundary value K2 of the preset error range can be obtained. Using the lower limit boundary value K1 and the upper limit boundary value K2 of the preset error range as boundaries, at least three reference distance ranges [0, K1), [K1, K2), and [K2, the sensing boundary of the ultrasonic sensor) can be divided. The calibration parameters of the reference distances [0, K1), [K1, K2), and [K2, the sensing boundary of the ultrasonic sensor] are the first calibration parameter, the second calibration parameter, and the third calibration parameter, respectively. For example, the first calibration parameter, the second calibration parameter, and the third calibration parameter are shown in Formulas 1-3 below:

[0096] X = x * a Formula 1

[0097] X = x * b Formula 2

[0098] X = x * b Formula 3

[0099] In Formulas 1-3, x represents the obstacle distance feedback value, and X represents the obstacle distance calibration value.

[0100] It is understandable that Formulas 1-3 show that the calibration parameters are currently determined by the simple product of the calibration coefficients (a in Formula 1, b in Formula 2, and c in Formula 3 can all be regarded as calibration coefficients) and the obstacle distance feedback value. Furthermore, in order to improve the calibration accuracy of the obstacle distance, air quality variables, humidity variables, etc. can also be added to the calibration parameters as calibration variables.

[0101] Therefore, different calibration parameters can be used to calibrate for different values ​​of obstacle distance feedback. This allows for calibration based on environmental interference at different distances, avoiding the problem of low data accuracy caused by increased environmental interference with greater distance in ultrasonic waves. This improves the calibration accuracy of obstacle distance to a certain extent, making the calibrated obstacle distance value closer to the actual distance of the obstacle, thereby improving the control accuracy of the robot and reducing robot collisions.

[0102] 203. The obstacle distance feedback value is calibrated according to the target calibration parameters to obtain the obstacle distance calibration value of the target ultrasonic sensor.

[0103] Among them, the obstacle distance calibration value refers to the obstacle distance (i.e., the distance between the robot and the obstacle) obtained after calibrating the obstacle distance feedback value.

[0104] For example, if the target calibration parameter is the first calibration parameter shown in Formula 1, then the obstacle distance x feedback value of the target ultrasonic sensor can be substituted into the first calibration parameter shown in Formula 1 to obtain the obstacle distance calibration value X of the target ultrasonic sensor.

[0105] 204. Control the robot's driving process based on the obstacle distance calibration value.

[0106] There are several ways to implement step 204, including, for example:

[0107] (1) If the obstacle distance calibration value is less than the preset stop distance threshold, the robot is controlled to stop moving; if the obstacle distance calibration value is greater than or equal to the preset stop distance threshold, the robot is controlled to move normally.

[0108] (2) To improve the safety of robot operation, two distance thresholds are set in this embodiment to generate control commands for the robot. In this case, step 204 may specifically include steps 2041A to 2042A:

[0109] 2041A. Based on the obstacle distance calibration value, a preset rotation distance threshold and a preset stop distance threshold are used to determine the robot's execution action.

[0110] The preset rotation distance threshold is the limit distance at which the robot cannot rotate.

[0111] The preset stopping distance threshold is the maximum distance the robot cannot move. The preset rotation distance threshold is greater than the preset stopping distance threshold.

[0112] For example, taking "the target ultrasonic sensor is at least one of a first ultrasonic sensor, a second ultrasonic sensor, a third sensor, a fourth ultrasonic sensor, and a fifth ultrasonic sensor" as an example, step 2041A may specifically include at least one of the following steps B1 to B5:

[0113] B1. If the target ultrasonic sensor is the first ultrasonic sensor located at the center of the front of the robot chassis, then the robot's execution action is determined based on the first obstacle distance calibration value of the first ultrasonic sensor and the first control rule of the first ultrasonic sensor.

[0114] The first control rule includes allowing the robot to rotate and prohibiting it from moving forward when the distance calibration value of the first obstacle is greater than the preset stop distance and less than the preset rotation distance threshold, and prohibiting the robot from moving forward when the distance calibration value of the first obstacle is less than or equal to the preset stop distance threshold.

[0115] The first obstacle distance calibration value refers to the obstacle distance calibration value of the first ultrasonic sensor. The method for determining the obstacle distance calibration value of the first ultrasonic sensor can be found in the previous explanation of "obstacle distance calibration value of the target ultrasonic sensor", which will not be repeated here.

[0116] B2. If the target ultrasonic sensor is a second ultrasonic sensor located on the left side of the robot chassis, the robot's execution action is determined based on the second obstacle distance calibration value of the second ultrasonic sensor and the second control rule of the second ultrasonic sensor.

[0117] The second control rule includes prohibiting the robot from rotating and allowing it to move forward when the distance calibration value of the second obstacle is less than or equal to a preset stop distance threshold;

[0118] The second obstacle distance calibration value refers to the obstacle distance calibration value of the second ultrasonic sensor. The method for determining the obstacle distance calibration value of the second ultrasonic sensor can be found in the previous explanation of "Obstacle Distance Calibration Value of Target Ultrasonic Sensor", which will not be repeated here.

[0119] B3. If the target ultrasonic sensor is a third ultrasonic sensor located on the right side of the robot chassis, the robot's execution action is determined based on the third obstacle distance calibration value of the third ultrasonic sensor and the third control rule of the third ultrasonic sensor.

[0120] The third control rule includes prohibiting the robot from rotating and allowing it to move forward when the distance calibration value of the third obstacle is less than or equal to the preset stop distance threshold.

[0121] The third obstacle distance calibration value refers to the obstacle distance calibration value of the third ultrasonic sensor. The method for determining the obstacle distance calibration value of the third ultrasonic sensor can be found in the previous explanation of "Obstacle Distance Calibration Value of Target Ultrasonic Sensor", which will not be repeated here.

[0122] B4. If the target ultrasonic sensor is the fourth ultrasonic sensor located at the left front position of the robot chassis, then the robot's execution action is determined based on the fourth obstacle distance calibration value of the fourth ultrasonic sensor and the fourth control rule of the fourth ultrasonic sensor.

[0123] The fourth control rule includes prohibiting the robot from moving forward and allowing it to rotate when the distance calibration value of the fourth obstacle is greater than the preset stop distance and less than the preset rotation distance threshold; and prohibiting the robot from rotating left and allowing it to rotate right when the distance calibration value of the fourth obstacle is less than or equal to the preset stop distance threshold.

[0124] The fourth obstacle distance calibration value refers to the obstacle distance calibration value of the fourth ultrasonic sensor. The method for determining the obstacle distance calibration value of the fourth ultrasonic sensor can be found in the previous explanation of "Obstacle Distance Calibration Value of Target Ultrasonic Sensor", which will not be repeated here.

[0125] B5. If the target ultrasonic sensor is the fifth ultrasonic sensor located at the right front of the robot chassis, then the robot's execution action is determined based on the fifth obstacle distance calibration value of the fifth ultrasonic sensor and the fifth control rule of the fifth ultrasonic sensor.

[0126] The fifth control rule includes prohibiting the robot from moving forward and allowing rotation when the distance calibration value of the fifth obstacle is greater than the preset stop distance and less than the preset rotation distance threshold, and prohibiting the robot from rotating right and allowing rotation left when the distance calibration value of the fifth obstacle is less than or equal to the preset stop distance threshold.

[0127] Among them, the fifth obstacle distance calibration value refers to the obstacle distance calibration value of the fifth ultrasonic sensor. The method for determining the obstacle distance calibration value of the fifth ultrasonic sensor can be found in the previous explanation of "obstacle distance calibration value of target ultrasonic sensor", which will not be repeated here.

[0128] For example, assuming there are three target ultrasonic sensors (such as a first ultrasonic sensor, a second ultrasonic sensor, and a third ultrasonic sensor), firstly, if the distance calibration value of the first obstacle is less than a preset rotation distance threshold but greater than a preset stop distance threshold, then under this condition, the robot is restricted to "allowing rotation and prohibiting forward movement"; secondly, if the distance calibration value of the second obstacle is less than or equal to the preset stop distance threshold, then under this condition, the robot is restricted to "prohibiting left rotation and allowing forward movement"; thirdly, if the distance calibration value of the third obstacle is less than or equal to the preset stop distance threshold, then under this condition, the robot is restricted to "prohibiting right rotation and allowing forward movement"; therefore, by combining the obstacle detection data of the first, second, and third ultrasonic sensors, it can be determined that the robot's action is "stop moving".

[0129] 2042A. Based on the executed action, generate motion control instructions for the robot to control the robot's driving process.

[0130] To facilitate understanding, let's continue with the example from step 2041A. For instance, if step 2042A determines that the robot's action is "stop driving", then in step 2042A, a control command to stop the robot is generated to control the robot's driving process, thereby preventing the robot from colliding with obstacles.

[0131] Therefore, by setting two distance thresholds—a preset rotation distance threshold and a preset stop distance threshold—to generate robot control commands, when transparent obstacles such as glass are detected, the robot can determine the actions it is allowed to perform and the actions it is prohibited to perform by combining the distance between the robot and the obstacle and the location of the ultrasonic sensor that detected the obstacle. This information is used to generate motion control commands for the robot to avoid collisions with obstacles and to avoid obstacles as much as possible, thereby reducing obstacle collisions while ensuring the robot's normal operation.

[0132] Furthermore, relying solely on motion control commands can only handle relatively critical situations. To improve the robot's ability to avoid obstacles such as glass, this embodiment uses obstacle distance calibration values ​​to mark the robot's obstacle map. This allows the robot to actively avoid obstacles that are relatively far away, such as glass, even when it recognizes them, thus reducing the risk of obstacle collisions. For example, to mark the positions of transparent objects such as glass for flexible obstacle avoidance and collision prevention, such as... Figure 5 As shown, the following steps 501 to 503 can be used for processing:

[0133] 501. Based on the fan-shaped detection area of ​​the target ultrasonic sensor and the obstacle distance calibration value, determine the position of the new obstacle detected by the target ultrasonic sensor.

[0134] For example, since ultrasonic sensors detect obstacles in the form of waves and cannot pinpoint their exact location, only providing a distance value, this embodiment expands the area corresponding to the obstacle distance calibration value to represent the obstacle (i.e., the new obstacle detected by the target ultrasonic sensor). There are various expansion methods. In some embodiments, the obstacle distance calibration value is used as the radius of a fan-shaped area, and the expansion of this fan-shaped area represents the new obstacle detected. The fan-shaped area of ​​the target ultrasonic sensor is then the location of the new obstacle detected. In some embodiments, the obstacle distance calibration value is used as the radius of a fan-shaped area, and a region with a preset angle is intercepted within the fan-shaped area of ​​the target ultrasonic sensor. This intercepted region with the preset angle is then expanded to represent the new obstacle detected. The intercepted region with the preset angle is then the location of the new obstacle detected by the target ultrasonic sensor.

[0135] 502. Based on the location of the newly detected obstacle, mark the newly detected obstacle on the obstacle map of the robot to obtain an updated obstacle map.

[0136] In some embodiments, the newly detected obstacle can be directly marked on the robot's obstacle map to obtain an updated obstacle map.

[0137] In some embodiments, since a larger obstacle distance calibration value results in a larger fan-shaped detection area of ​​the target ultrasonic sensor, the expansion and dilation represent more filling points for newly detected obstacles, leading to lower accuracy of the newly detected obstacles. To improve the accuracy of newly detected obstacles and avoid situations where the machine can bypass obstacles that are actually beyond the actual obstacle range, this embodiment obtains a calibration distance threshold for the obstacle distance feedback value. If the obstacle distance feedback value is less than the calibration distance threshold, the newly detected obstacle is marked on the robot's obstacle map based on its position, resulting in an updated obstacle map. If the obstacle distance feedback value is greater than or equal to the calibration distance threshold, the newly detected obstacle is not marked on the robot's obstacle map. Thus, the marking distance can be limited, and the newly detected obstacle is only calibrated when the obstacle distance feedback value is less than the calibration distance threshold, reducing the occurrence of situations where the machine can bypass obstacles that are actually beyond the actual obstacle range.

[0138] Furthermore, to improve the accuracy of newly detected obstacles, the robot's current moving speed is obtained. Based on the current moving speed, a calibration distance threshold for the obstacle distance feedback value is determined, wherein the current moving speed is positively correlated with the calibration distance threshold. This ensures that the greater the robot's speed, the greater the calibration distance, and vice versa. Ideally, the robot does not mark newly detected obstacles when it stops, ensuring that the robot can start walking normally.

[0139] Furthermore, since the ultrasonic sensor projects a fan-shaped detection surface at a certain angle, there is a blind zone in the detection angle. This can cause the robot to oscillate while walking, meaning that if the robot turns around, it may not detect the obstacle, mistakenly believe there is no obstacle, and then return to the obstacle. By acquiring the cumulative marking duration of the newly detected obstacle, if the cumulative marking duration exceeds a preset marking duration threshold, the newly detected obstacle is deleted from the obstacle map. This allows the use of a marking decay mechanism to mark the newly detected obstacle, maintaining its mark on the obstacle map for a preset marking duration threshold (e.g., 20 seconds). When the newly detected obstacle is detected again, the time calculation restarts, ensuring the continuity of the marking, improving the robot's obstacle avoidance efficiency, and reducing the problem of the robot repeatedly entering obstacle areas.

[0140] 503. Based on the updated obstacle map, control the robot to avoid obstacles.

[0141] To better understand the embodiments of this application, the following example illustrates the robot collision avoidance method: "A robot equipped with multiple ultrasonic sensors, using obstacle detection results from both ultrasonic and laser sensors for collision avoidance processing." Please refer to [link / reference]. Figure 6 The robot collision avoidance process can be as follows:

[0142] 1. Obtain ultrasonic sensing data from each ultrasonic sensor installed on the robot. (Reference) Figure 6 (As shown in the "Ultrasonic Sensor Data Acquisition" section)

[0143] 2. The ultrasonic sensing data of each ultrasonic sensor is calibrated to obtain the obstacle distance calibration value for each ultrasonic sensor by calibrating the obstacle distance feedback value of each ultrasonic sensor. (Reference) Figure 6 (As shown in the "Stage Calibration of Ultrasonic Sensor Data" section)

[0144] For specific implementation details, please refer to steps 201-203, which will not be elaborated here.

[0145] 3. By fusing obstacle detection results from ultrasonic sensors and laser sensors, determine whether to use ultrasonic sensors or laser sensors for obstacle identification information. (Reference) Figure 6 (As shown in the "Multi-sensor Fusion" section)

[0146] For specific implementation details, please refer to steps 401 to 411, which will not be elaborated here.

[0147] 4. Use obstacle recognition information from ultrasonic or laser sensors to generate motion control commands for the robot. (Reference) Figure 6 (As shown in the "Generate Motion Control Instructions" section)

[0148] For specific implementation details, please refer to steps 401-411 and steps 2041A-2042A, which will not be elaborated here.

[0149] 5. Use obstacle recognition information from ultrasonic or laser sensors to mark obstacles on the robot's obstacle map. (Reference) Figure 6 (As shown in the "Generate Cost Map" section)

[0150] For specific implementation details, please refer to steps 401 to 411, which will not be elaborated here.

[0151] 6. Use the robot's obstacle map to control the robot to avoid obstacles.

[0152] As can be seen from the above, firstly, by setting different calibration parameters for different reference distance ranges; determining the target calibration parameters for the obstacle distance feedback value of the target ultrasonic sensor based on the reference distance range associated with each preset calibration parameter; and calibrating the obstacle distance feedback value according to the target calibration parameters to obtain the obstacle distance calibration value of the target ultrasonic sensor, different calibration parameters can be used to calibrate for different obstacle distance calibration values. This allows for calibration using different calibration parameters to address environmental interference at different distances, avoiding the problem of low data accuracy caused by increased environmental interference with increasing distance. This improves the calibration accuracy of obstacle distance to a certain extent, making the obstacle distance calibration value closer to the actual distance of the obstacle, thereby improving the recognition accuracy of obstacle identification using ultrasonic sensors and reducing robot collisions. Secondly, by utilizing ultrasonic sensors, transparent obstacles such as glass can be effectively identified, increasing the probability of identifying transparent obstacles such as glass during robot navigation, thereby reducing collisions between the robot and transparent obstacles such as glass. Therefore, the embodiments of this application can improve the recognition accuracy of obstacles, especially transparent obstacles, to a certain extent, reduce the probability of robot collisions with obstacles, and improve the operational safety of the robot.

[0153] Those skilled in the art will understand that all or part of the steps in the above-described robot collision avoidance method can be accomplished by instructions, or by controlling related hardware with instructions. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0154] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of computer programs that can be loaded by a processor to execute any of the robot collision avoidance methods provided in embodiments of this application. For example, the computer program can be loaded by a processor to perform the following steps:

[0155] Obtain obstacle distance feedback values ​​from target ultrasonic sensors installed on the robot; determine target calibration parameters for the obstacle distance feedback values ​​based on preset reference distance ranges associated with each calibration parameter; calibrate the obstacle distance feedback values ​​according to the target calibration parameters to obtain obstacle distance calibration values ​​for the target ultrasonic sensors; control the robot's movement based on the obstacle distance calibration values.

[0156] In some embodiments, the computer program can be loaded by a processor to perform the following steps:

[0157] Based on the obstacle distance calibration value, a preset rotation distance threshold and a preset stop distance threshold are used to determine the robot's execution action; based on the execution action, motion control commands for the robot are generated to control the robot's movement process.

[0158] In some embodiments, the computer program can be loaded by a processor to perform the following steps:

[0159] Obtain the first obstacle detection result of each ultrasonic sensor installed on the robot; use each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected as the target ultrasonic sensor.

[0160] In some embodiments, the computer program can be loaded by a processor to perform the following steps:

[0161] Each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected is used as a preliminary screening ultrasonic sensor; the second obstacle detection result of the robot's laser-type sensor at the detection position corresponding to the preliminary screening ultrasonic sensor is obtained; if the second obstacle detection result indicates that no obstacle has been detected, the preliminary screening ultrasonic sensor is used as the target ultrasonic sensor.

[0162] In some embodiments, the computer program can be loaded by a processor to perform the following steps:

[0163] Based on the fan-shaped detection area of ​​the target ultrasonic sensor and the obstacle distance calibration value, the position of the newly detected obstacle by the target ultrasonic sensor is determined; based on the position of the newly detected obstacle, the newly detected obstacle is marked on the obstacle map of the robot to obtain an updated obstacle map; based on the updated obstacle map, the robot is controlled to avoid obstacles.

[0164] In some embodiments, the computer program can be loaded by a processor to perform the following steps:

[0165] Obtain the calibration distance threshold of the obstacle distance feedback value; if the obstacle distance feedback value is less than the calibration distance threshold, mark the newly detected obstacle on the robot's obstacle map based on the position of the newly detected obstacle to obtain an updated obstacle map.

[0166] In some embodiments, the computer program can be loaded by a processor to perform the following steps:

[0167] The robot's current moving speed is obtained; based on the current moving speed, a calibration distance threshold for the obstacle distance feedback value is determined, wherein the current moving speed is positively correlated with the calibration distance threshold.

[0168] In some embodiments, the computer program can be loaded by a processor to perform the following steps:

[0169] Obtain the cumulative marking duration of the newly detected obstacle; if the cumulative marking duration is greater than a preset marking duration threshold, then delete the newly detected obstacle from the obstacle map.

[0170] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0171] In the above embodiments of the robot collision avoidance method, computer-readable storage medium, and self-moving device, the descriptions of each embodiment have different focuses. Parts not described in detail in a particular embodiment can be found in the relevant descriptions of other embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes and beneficial effects of the computer-readable storage medium, self-moving device, and their corresponding units described above can be referred to the description of the robot collision avoidance method in the above embodiments, and will not be repeated here.

[0172] The above provides a detailed description of a robot collision avoidance method, a self-moving device, and a computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A robot collision avoidance method, characterized in that, The method includes: Obtain obstacle distance feedback values ​​from the target ultrasonic sensors installed on the robot; Based on the preset reference distance range associated with each calibration parameter, the target calibration parameters for the obstacle distance feedback value are determined; The obstacle distance feedback value is calibrated according to the target calibration parameters to obtain the obstacle distance calibration value of the target ultrasonic sensor; The robot's movement is controlled based on the obstacle distance calibration value. The robot is equipped with multiple ultrasonic sensors, and the method further includes: Obtain the first obstacle detection result for each ultrasonic sensor installed on the robot; Each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected is designated as the target ultrasonic sensor. The step of using each ultrasonic sensor whose first obstacle detection result indicates that an obstacle has been detected as the target ultrasonic sensor includes: Each ultrasonic sensor that detected an obstacle is used as a preliminary screening ultrasonic sensor. Obtain the second obstacle detection result of the robot's laser sensor at the detection position corresponding to the initial screening ultrasonic sensor; If the second obstacle detection result is that no obstacle is detected, then the initial screening ultrasonic sensor is used as the target ultrasonic sensor.

2. The robot collision avoidance method according to claim 1, characterized in that, The step of controlling the robot's movement based on the obstacle distance calibration value includes: Based on the obstacle distance calibration value, a preset rotation distance threshold and a preset stop distance threshold are used to determine the robot's execution action; Based on the executed actions, motion control commands are generated for the robot to control its movement.

3. The robot collision avoidance method according to claim 1, characterized in that, The ultrasonic sensors installed on the robot include at least a first ultrasonic sensor located at the center of the front of the robot chassis, a second ultrasonic sensor located at the left side of the robot chassis, a third ultrasonic sensor located at the right side of the robot chassis, a fourth ultrasonic sensor located at the front left of the robot chassis, and a fifth ultrasonic sensor located at the front right of the robot chassis.

4. The robot collision avoidance method according to claim 1, characterized in that, The preset calibration parameters include a first calibration parameter, a second calibration parameter, and a third calibration parameter; The upper boundary value of the reference distance range associated with the first calibration parameter is the first boundary value; The lower boundary value of the reference distance range associated with the second calibration parameter is the first boundary value, and the upper boundary value of the reference distance range associated with the second calibration parameter is the second boundary value; The lower limit boundary value of the reference distance range associated with the third calibration parameter is the second boundary value; The first boundary value is the same as the lower boundary value of the preset error range, and the second boundary value is the same as the upper boundary value of the preset error range. The preset error range is the range of values ​​for the target obstacle distance feedback value. The target obstacle distance feedback value refers to the obstacle distance feedback value whose difference from the true obstacle distance is less than the error distance of the laser sensor.

5. The robot collision avoidance method according to claim 1, characterized in that, The method further includes: Based on the fan-shaped detection area of ​​the target ultrasonic sensor and the obstacle distance calibration value, the position of the new obstacle detected by the target ultrasonic sensor is determined. Based on the location of the newly detected obstacle, the newly detected obstacle is marked on the robot's obstacle map to obtain an updated obstacle map; Based on the updated obstacle map, the robot is controlled to avoid obstacles.

6. The robot collision avoidance method according to claim 5, characterized in that, The step of marking the newly detected obstacle on the robot's obstacle map based on the location of the newly detected obstacle to obtain an updated obstacle map includes: Obtain the calibration distance threshold of the obstacle distance feedback value; If the obstacle distance feedback value is less than the calibrated distance threshold, then based on the position of the newly detected obstacle, the newly detected obstacle is marked on the robot's obstacle map to obtain an updated obstacle map.

7. The robot collision avoidance method according to claim 6, characterized in that, The calibration distance threshold for obtaining the obstacle distance feedback value includes: Obtain the robot's current moving speed; Based on the current moving speed, a calibration distance threshold for the obstacle distance feedback value is determined, wherein the current moving speed is positively correlated with the calibration distance threshold.

8. The robot collision avoidance method according to claim 5, characterized in that, The method further includes: Obtain the cumulative marking duration of the newly detected obstacles; If the cumulative marking duration exceeds a preset marking duration threshold, the newly detected obstacle will be removed from the obstacle map.

9. A self-moving device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the robot collision avoidance method as described in any one of claims 1 to 8 when it invokes the computer program in the memory.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to execute the robot collision avoidance method according to any one of claims 1 to 8.

Images