Robot-based space active safety obstacle avoidance method and device, and storage medium

Abstract

The application provides a kind of space active safety barrier avoidance method, device and storage medium based on robot, the method is determined by industrial computer: based on the state information of target robot and / or each device pose information, determine the monitoring area corresponding to each monitoring device;According to each monitoring area, target monitoring area is generated by combination;Based on the point cloud information corresponding to the target monitoring area, it is judged whether there is barrier area in the target monitoring area;When it is judged that the target monitoring area exists the barrier area, control the target robot to avoid barrier.This application determines monitoring area according to the device pose information of multiple monitoring devices, combined with the state information of robot, so as to adopt multiple monitoring devices to avoid barrier monitoring, improve the accuracy of robot barrier avoidance, avoid the problem of inaccurate robot barrier avoidance caused by single monitoring direction of single monitoring device.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robots, in particular to a space active safe obstacle avoidance method based on robots, a device and a computer readable storage medium. BACKGROUND

[0002] With the rapid development and progress of artificial intelligence technology, the intelligentization of robots has become the ultimate goal of modern robot development. With the continuous improvement of the development speed of robots, the application range is also expanding, and robots assist or replace people in many fields to achieve efficiency improvement and precision improvement. In the field of mobile robots, 2D laser radar is currently widely used as a sensor for perceiving the surrounding environment. In the process of robot movement, the data of laser radar is used as the basis for judging whether there is an obstacle in the moving direction. Due to the characteristics of 2D laser sensor, it can only perceive the information of a plane parallel to the ground and the same height as the laser radar, and cannot perceive the obstacles outside the plane, unpredictable dangers, and cannot accurately avoid obstacles when there are obstacles outside the plane. A small part of robots use 3D vision sensors for obstacle avoidance, but only use one sensor to illuminate a single direction, which cannot take into account obstacle avoidance when the robot moves or acts in other directions, which may cause certain damage to the robot. Therefore, how to solve the inaccurate robot obstacle avoidance has become a technical problem to be solved. SUMMARY

[0003] The main purpose of the present application is to provide a space active safe obstacle avoidance method based on robots, devices, equipment and computer readable storage media, aiming at solving the problem of inaccurate robot obstacle avoidance.

[0004] To achieve the above purpose, the present application provides a space active safe obstacle avoidance method based on robots, which obtains the device pose information of a plurality of monitoring devices corresponding to a target robot through an industrial computer, and determines the monitoring area corresponding to each monitoring device according to the state information of the target robot and / or each device pose information. According to each monitoring area, the target monitoring area is generated by combination; based on the point cloud information corresponding to the target monitoring area, it is judged whether there is an obstacle area in the target monitoring area; when it is judged that there is an obstacle area in the target monitoring area, the target robot is controlled to avoid obstacles.

[0005] Further, in order to achieve the above object, the application further provides a robot-based space active safety obstacle avoidance device, which is applied to an industrial computer, and comprises: a monitoring area generation module, configured to acquire device pose information of a plurality of monitoring devices corresponding to a target robot through the industrial computer, and determine a monitoring area corresponding to each of the monitoring devices according to state information of the target robot and / or each of the device pose information; a monitoring area combination module, configured to combine and generate a target monitoring area according to each of the monitoring areas through the industrial computer; an obstacle area judgment module, configured to judge whether there is an obstacle area in the target monitoring area based on point cloud information corresponding to the target monitoring area through the industrial computer; and an obstacle avoidance signal sending module, configured to control the target robot to perform obstacle avoidance when it is judged that there is the obstacle area in the target monitoring area through the industrial computer.

[0006] Further, in order to achieve the above object, the application further provides a robot-based space active safety obstacle avoidance device, which comprises a processor, a memory, and an obstacle avoidance program stored in the memory and executable by the processor, wherein the obstacle avoidance program is executed by the processor to implement the steps of the above robot-based space active safety obstacle avoidance method.

[0007] Further, in order to achieve the above object, the application further provides a computer readable storage medium, which stores a robot-based space active safety obstacle avoidance program, wherein the robot-based space active safety obstacle avoidance program is executed by a processor to implement the steps of the above robot-based space active safety obstacle avoidance method.

[0008] The application provides a robot-based space active safety obstacle avoidance method, device, equipment and computer readable storage medium, wherein the method comprises the following steps of: acquiring device pose information of a plurality of monitoring devices corresponding to a target robot through an industrial computer, and determining a monitoring area corresponding to each of the monitoring devices according to state information of the target robot and / or each of the device pose information; combining and generating a target monitoring area according to each of the monitoring areas; judging whether there is an obstacle area in the target monitoring area based on point cloud information corresponding to the target monitoring area; and controlling the target robot to perform obstacle avoidance when it is judged that there is the obstacle area in the target monitoring area. In the above manner, the target monitoring area is generated according to the state information of the robot and / or the device pose information of each monitoring device, and the monitoring area is determined according to the device pose information of the plurality of monitoring devices in combination with the state information of the robot, so that the plurality of monitoring devices are used for obstacle avoidance monitoring, the obstacle avoidance accuracy of the robot is improved, and the problem of inaccurate robot obstacle avoidance caused by single monitoring direction of a single monitoring device is avoided. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 A hardware structure schematic diagram of a space active safety obstacle avoidance device based on a robot involved in an embodiment of the present application is shown in the figure.

[0010] Figure 2 A flowchart of a first embodiment of a space active safety obstacle avoidance method based on a robot is shown in the figure.

[0011] Figure 3 A flowchart of a second embodiment of a space active safety obstacle avoidance method based on a robot is shown in the figure.

[0012] Figure 4 A flowchart of a third embodiment of a space active safety obstacle avoidance method based on a robot is shown in the figure.

[0013] Figure 5 A flowchart of a fourth embodiment of a space active safety obstacle avoidance method based on a robot is shown in the figure.

[0014] Figure 6 A functional module schematic diagram of an industrial computer is shown in the figure.

[0015] The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0016] It should be understood that the specific embodiments described herein are merely intended to explain the present application and not to limit the present application.

[0017] The obstacle avoidance method involved in the embodiments of the present application is mainly applied to an obstacle avoidance device, which can be a PC, a portable computer, a mobile terminal or the like device having a display and processing function.

[0018] Reference Figure 1 , Figure 1 A hardware structure schematic diagram of an obstacle avoidance device involved in an embodiment of the present application is shown in the figure. In the embodiments of the present application, the obstacle avoidance device includes a processor 1001 (for example, a CPU), a communication bus 1002, a user interface 1003, a network interface 1004 and a memory 1005. The communication bus 1002 is used to realize the connection and communication among these components; the user interface 1003 includes a display screen (Display) and an input unit such as a keyboard (Keyboard); the network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface); the memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory) such as a disk memory, and the memory 1005 can optionally be a storage device independent of the aforementioned processor 1001.

[0019] Those skilled in the art can understand that, Figure 1 The hardware structure shown in the above embodiment does not constitute a limitation on the obstacle avoidance device, and includes more or fewer components than the diagram, or combines certain components, or different component arrangements.

[0020] The embodiment of the present application provides a robot-based active safety obstacle avoidance method in space.

[0021] Referring to Figure 2 , Figure 2 FIG. 1 is a flowchart of a robot-based active safety obstacle avoidance method in space according to an embodiment of the present application.

[0022] In the embodiment, the robot-based active safety obstacle avoidance method in space is applied to an industrial PC of a robot, and the obstacle avoidance method comprises the following steps:

[0023] In step S10, the industrial PC obtains device pose information of a plurality of monitoring devices corresponding to a target robot, and determines a monitoring area corresponding to each monitoring device according to state information of the target robot and / or each device pose information.

[0024] In the embodiment, the monitoring device is a sensor device capable of communicating with the target robot and obtaining 3D point cloud, such as a 3D camera, a 3D laser radar, a stereo camera, a time-of-flight camera, etc. Specifically, the plurality of monitoring devices can be installed at predetermined positions of the target robot, such as the front of the target robot, the rear of the target robot, etc., so as to improve the obstacle avoidance accuracy of the target robot. In addition, the plurality of monitoring devices can also be existing monitoring cameras, which are in communication connection with the target robot, so as to reduce the obstacle avoidance cost of the target robot.

[0025] The monitoring device uses the principle of laser ranging to record the three-dimensional coordinates, reflectivity and texture information of a large number of dense points on the surface of the measured object, and can quickly reconstruct the three-dimensional model of the measured target and various data such as lines, surfaces and bodies. Among them, the device pose information of the monitoring device relative to the center of the robot includes x, y, z and roll, pitch, yaw and other parameter information.

[0026] Further, the application also provides an industrial computer and a system. A communication module is added to the host computer of the target robot, data processing of a plurality of monitoring devices is transferred to another industrial computer, and monitoring and obstacle avoidance information is sent to the host industrial computer of the target robot in real time through TCP, so that the target robot can complete obstacle avoidance in multiple directions without affecting the basic functions of the robot. Therefore, the obstacle avoidance ability of the target robot is improved, and the problem that the CPU occupied by data processing of a plurality of monitoring devices is too large to cause the target robot to be unable to operate normally is solved.

[0027] In step S20, the industrial computer combines and generates a target monitoring area according to each monitoring area.

[0028] In this embodiment, each monitoring area is summarized to generate a table Table, and each monitoring area in the table Table is combined to generate the target monitoring area Area.

[0029] In step S30, the industrial computer determines whether there is an obstacle area in the target monitoring area based on the point cloud information corresponding to the target monitoring area.

[0030] In this embodiment, the industrial computer determines the pose of the target robot through a software reading function, and obtains the relative pose between the pose of the monitoring device and the pose of the target robot through calculation, wherein the relative pose is a correlation matrix T.

[0031] In this embodiment, the monitoring device takes a 3D camera as an example. The device pose information can be obtained by using the camera internal parameter to transform a three-dimensional space point in the camera coordinate system to the imaging plane coordinate system. After the lens distortion correction process, the three-dimensional space point can be further transformed to a two-dimensional pixel point in the image pixel coordinate system. Therefore, there is a mapping relationship between the projection point in the image pixel coordinate system and the three-dimensional space point in the camera coordinate system. The specific steps of transformation are as follows.

[0032] The camera internal parameter, referred to as the internal parameter, is only related to the internal properties of the camera, such as focal length, resolution, pixel size, etc. The coordinate conversion relationship between the camera coordinate system and the world coordinate system is called the camera external parameter, which generally consists of two parts: translation and rotation. The camera takes a picture of the target object in the working range to obtain an image, and establishes a mapping relationship between the three-dimensional space point in the camera coordinate system and the corresponding point in the image pixel coordinate system through the camera internal parameter.

[0033] The three-dimensional space point in the camera coordinate system is converted to the world coordinate system through the camera external parameter. According to the internal and external parameters, a mapping relationship between the pixel point in the image pixel coordinate system and the three-dimensional space point in the world coordinate system is constructed.

[0034] According to the image processing algorithm, the target point on the image is obtained, and through the mapping relationship from the pixel coordinate system to the world coordinate system, a three-dimensional space target point based on the world coordinate system is obtained.

[0035] Specifically, the world coordinate system has coordinate axes Xw, Yw and Zw, and a user-defined three-dimensional coordinate system in space is used to describe the coordinate positions between objects and cameras in a three-dimensional space, and satisfies the right-hand rule.

[0036] The camera coordinate system has coordinate axes Xc, Yc and Zc, and the optical center of the camera is used as the origin, the Zc axis coincides with the optical axis and is perpendicular to the imaging plane, and the photographic direction is taken as the positive direction, and the Xc and Yc axes are parallel to the x and y axes of the image physical coordinate system.

[0037] The pixel coordinate system is established with the upper left corner of the image as the origin, and a rectangular coordinate system u-v in pixels is established. The horizontal coordinate u and the vertical coordinate v of the pixel are the column number and the row number in the image array. Since (u, v) only represents the column number and the row number of the pixel, and the position of the pixel in the image is not represented in physical units, an image coordinate system x-y represented in physical units (such as millimeters) is also established. The intersection of the camera optical axis and the image plane (generally located at the center of the image plane, also called the principal point of the image) is defined as the origin O1 of the coordinate system, and the x axis is parallel to the u axis and the y axis is parallel to the v axis. Assuming that (u0, v0) represents the coordinates of O1 in the u-v coordinate system, dx and dy represent the physical dimensions of each pixel on the horizontal axis x and the vertical axis y, respectively, then there is a relationship between the coordinates of each pixel in the u-v coordinate system and the coordinates in the x-y coordinate system as follows:

[0038]

[0039]

[0040] Assuming that the unit in the physical coordinate system is millimeters, then the unit of dx is: millimeters / pixel, and the unit of x / dx is pixel, that is, the unit of u.

[0041] In this embodiment, the manner of determining the obstacle region can be to scan the obstacle point cloud information by the monitoring device, to determine the obstacle point cloud information Cloud_C, and to transform the obstacle point cloud information into the robot coordinate system according to the correlation matrix transformation, to obtain the obstacle region Cloud_Robot, that is:

[0042] Cloud_Robot=T*Cloud_C.

[0043] Step S40, when the industrial computer determines that the target monitoring area has the obstacle area, the industrial computer controls the target robot to avoid the obstacle.

[0044] In this embodiment, the range of the obstacle area Cloud_Robot is obtained through step S30, and step S40 determines whether the target monitoring area has the obstacle area Cloud_Robot.

[0045] The embodiment provides a robot-based active safety obstacle avoidance method in space, which comprises the following steps: an industrial computer acquires device pose information of a plurality of monitoring devices corresponding to a target robot, and determines a monitoring area corresponding to each monitoring device according to state information of the target robot and / or the device pose information; a target monitoring area is generated by combining each monitoring area; whether the target monitoring area has an obstacle area is determined based on point cloud information corresponding to the target monitoring area; and when it is determined that the target monitoring area has the obstacle area, the target robot is controlled to avoid the obstacle. In the above manner, the target monitoring area is generated according to the state information of the robot and / or the device pose information of each monitoring device, and the monitoring area is determined according to the device pose information of the plurality of monitoring devices and the state information of the robot, so that the plurality of monitoring devices are used for obstacle avoidance monitoring, the obstacle avoidance accuracy of the robot is improved, and the problem of inaccurate robot obstacle avoidance caused by single monitoring direction of a single monitoring device is avoided.

[0046] Reference Figure 3 , Figure 3 FIG. 1 is a flowchart of a robot-based active safety obstacle avoidance method in space according to a first embodiment of the present application.

[0047] Based on the above Figure 2 mentioned embodiment, in this embodiment, step S10 specifically comprises:

[0048] Step S11, the industrial computer acquires an installation position and a monitoring angle of each monitoring device corresponding to the target robot as device pose information of each monitoring device.

[0049] Step S12, the industrial computer determines the monitoring area corresponding to each monitoring device based on the installation position and the monitoring angle of each monitoring device.

[0050] In this embodiment, each monitoring device is installed in each direction of the target robot, and the monitoring angle can be set according to the monitoring area ID, and the initial monitoring area can also be set through the monitoring area ID when the target robot is started.

[0051] This embodiment provides a robot-based active obstacle avoidance method for space safety. The method determines the monitoring area based on the device pose information, and then combines the monitoring areas to generate a target monitoring area. Based on the point cloud information corresponding to the target monitoring area, it determines whether an obstacle area exists within the target monitoring area. When an obstacle area is determined to exist in the target monitoring area, the method controls the target robot to avoid the obstacle. Therefore, by determining the monitoring area based on multiple device pose information, the method avoids the limitation of a single monitoring device having a single monitoring direction, thus improving obstacle avoidance accuracy.

[0052] Reference Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the robot-based active obstacle avoidance method for space safety according to the present invention.

[0053] Based on the above Figure 3 The second embodiment shown in this embodiment further includes the following steps after step S12:

[0054] Step S13, the industrial control computer acquires the position, moving speed and / or moving direction of the target robot as the status information;

[0055] In step S14, the industrial control computer adjusts the monitoring area of ​​each monitoring device according to the position, moving speed and / or moving direction of the target robot.

[0056] In this embodiment, based on the initial monitoring area, the monitoring area changes accordingly depending on the state information of the target robot. For example, if the target robot's movement speed increases, the corresponding target monitoring area expands; if the target robot moves forward, the corresponding target monitoring area moves to the front of the target robot. In other words, the monitoring area is determined not only by the device pose information but also by the device pose information combined with the state information.

[0057] This embodiment provides a robot-based active obstacle avoidance method for space safety. The method determines the monitoring area based on the device pose information and the state information, and then combines the monitoring areas to generate a target monitoring area. Based on the point cloud information corresponding to the target monitoring area, it determines whether an obstacle area exists within the target monitoring area. When an obstacle area is determined to exist in the target monitoring area, the method controls the target robot to avoid the obstacle. Therefore, by dynamically determining the monitoring area based on the pose information and state information of multiple monitoring devices, the method avoids the single monitoring direction of a single monitoring device and improves obstacle avoidance accuracy.

[0058] Reference Figure 5 , Figure 5A flowchart of a fourth embodiment of a robot-based space active safety obstacle avoidance method of the present application.

[0059] Based on the above Figure 2 As shown in the embodiment, in the step S10, specifically includes:

[0060] In step S01, the industrial computer obtains the position, moving speed and / or moving direction of the target robot as the state information.

[0061] In step S02, the industrial computer obtains the initial monitoring area corresponding to each monitoring device, adjusts the initial monitoring area corresponding to each monitoring device according to the position, moving speed and / or moving direction of the target robot, and determines the monitoring area corresponding to each monitoring device.

[0062] In this embodiment, according to the state information, the industrial computer generates different monitoring area IDs, and can adjust the range of the monitoring area according to different state information. Each bit of the monitoring area ID corresponds to a state, for example, the first bit of the monitoring area ID represents the speed, 1 represents high speed, and 0 represents low speed. When the first bit of the monitoring area ID is 1, the target robot travels at high speed, and the corresponding monitoring area will be correspondingly enlarged.

[0063] The embodiment provides a robot-based space active safety obstacle avoidance method, which determines the monitoring area according to the state information, and then combines the monitoring area to generate the target monitoring area; judges whether there is an obstacle area in the target monitoring area based on the point cloud information corresponding to the target monitoring area; and controls the target robot to avoid obstacles when it is determined that there is an obstacle area in the target monitoring area. Thus, according to the state information and the real-time state of the target robot, the monitoring area is dynamically determined, the monitoring direction of a single monitoring device is avoided, the failure of obstacle avoidance caused by the changing state of the target robot is effectively avoided, and the obstacle avoidance accuracy is improved.

[0064] Further, after the step S10, the method further includes:

[0065] The industrial computer determines the IP address of the monitoring device according to the specific installation position of the monitoring device, so that the monitoring device communicates with the industrial computer through the IP address.

[0066] Based on the above embodiment, the present application provides a method for preventing the industrial computer from being damaged due to the shutdown of the host computer.

[0067] When the device is powered on, the industrial computer waits for the host to query whether to avoid obstacles. When the first query arrives, it indicates that the host has started working normally. If the query time interval is more than 5s thereafter, it can be considered that the host has been powered off or restarted. If no signal of the host restarting is received, it is considered that the host is powered off. The device also automatically powers off to prevent damage caused by sudden power failure of the industrial computer. If the signal of the host restarting is received, it reenters the state of waiting for the host to query whether to avoid obstacles.

[0068] Specifically, the method for preventing the host from powering off to cause damage to the industrial computer is applied to the industrial computer. The method for preventing the host from powering off to cause damage to the industrial computer comprises the following steps:

[0069] a. Waiting for the host to query obstacle avoidance information. After the program is started, a TCP connection is established with the host. The host is queried until the first query instruction arrives. Then, the subsequent monitoring link is started to avoid the host from powering off due to the delay in connection after the program is started and the monitoring timeout.

[0070] b. Recording the current query time. When the TCP thread of the industrial computer receives the signal of the host querying obstacle avoidance information, the current system time is recorded as t1.

[0071] c. Recording the current system time as t2.

[0072] d. Judging whether the signal of the host querying obstacle avoidance information is received. If the TCP thread of the industrial computer receives the signal of the host querying obstacle avoidance information, the current system time is recorded as t1. If the TCP thread of the industrial computer does not receive the signal of the host querying obstacle avoidance information, the next judgment is entered.

[0073] e. Judging whether the interval between the current time and the latest query time of the host is greater than 5s. If t2-t1≤5s, the current system time is recorded as t2 again. If t2-t1>5s, the next judgment is entered.

[0074] f. Judging whether the signal of the host restarting is received. If the signal of the host restarting is received, it indicates that the communication interruption is caused by the host restarting, not the host powering off. Therefore, it returns to the step a of waiting for the host to query obstacle avoidance information. If the signal of the host restarting is not received, it indicates that the communication interruption is caused by the host powering off. Therefore, the industrial computer is about to be powered off to avoid damage to the industrial computer caused by sudden power failure of the host.

[0075] Based on the above embodiment, the step S30 specifically comprises:

[0076] a. The industrial computer acquires the target robot pose information and the initial pose information of each monitoring device, and calculates the relative pose relationship between the initial pose information and the target robot pose information;

[0077] b. The industrial computer acquires the point cloud information scanned by each monitoring device, and converts the point cloud information scanned by each monitoring device into the corresponding point cloud information of the target robot according to the relative pose relationship, as the point cloud information corresponding to the target monitoring area;

[0078] In the above embodiments, it is determined whether there is an obstacle area in the target monitoring area, that is, whether the obstacle area and the target monitoring area overlap, thereby providing an overlapping area extraction method based on region segmentation:

[0079] a. The point clouds of the fault area and the target monitoring area are confirmed respectively;

[0080] b. Each point cloud region is segmented according to the geometric structure features by spectral clustering;

[0081] c. An ESF multidimensional shape descriptor is established for each region, and the Euclidean distance between the extracted descriptors is calculated, and the region with the closest Euclidean distance between the descriptors is the overlapping region between the point clouds.

[0082] Based on the above embodiments, step S40 further comprises:

[0083] If the industrial computer determines that the target monitoring area does not contain the obstacle area, no obstacle avoidance signal is sent to the target robot.

[0084] The application also provides a robot-based space active safety obstacle avoidance method, which is applied to the robot, and comprises the following steps:

[0085] When the robot detects that the monitoring area ID changes, the robot sends an instruction to change the monitoring area ID to the industrial computer, wherein the robot is connected to the industrial computer through a TCP protocol;

[0086] The robot queries the industrial computer for obstacle avoidance and issues an obstacle avoidance instruction to the action module.

[0087] The robot detects the change of the monitoring area ID when the robot detects the change of the monitoring area ID, and sends an instruction to change the monitoring area ID to the industrial computer.

[0088] The robot starts a thread to query the monitoring area ID, and detects whether the monitoring area ID changes;

[0089] If the monitoring area ID of the robot changes, the robot sends an instruction to change the monitoring area ID to the industrial computer.

[0090] If the monitoring area ID of the robot does not change, return to the step of starting a thread to query the monitoring area ID and detecting whether the monitoring area ID changes.

[0091] In this embodiment, a TCP server is created to facilitate connection with the host computer, and wait for the host computer to connect with the industrial computer through the TCP thread. When receiving the signal sent by the host computer, the signal sent by the host computer is parsed, preprocessed, the signal category is judged, and the corresponding data is transmitted according to the signal category.

[0092] Specifically, the robot sets the front and rear monitoring area IDs through the industrial computer, and updates the current monitoring area according to the monitoring area ID; the robot sets the monitoring area corresponding to each monitoring area ID through the industrial computer; the robot queries the current monitoring area ID through the industrial computer; the robot sets the host computer restart state through the industrial computer.

[0093] Further, the robot starts a thread to subscribe to the current monitoring area ID of the industrial computer:

[0094] The host computer subscribes to the current monitoring area ID of the industrial computer to determine whether the obstacle avoidance area has been updated, and judges it in combination with the next step; query whether the current monitoring area ID of the host computer has changed, if it has changed, send an instruction to change the monitoring area ID to the industrial computer, if it has not changed, continue to query, and return to step a.

[0095] Further, the robot queries the obstacle avoidance to the industrial computer and issues an obstacle avoidance instruction to the action module.

[0096] In this embodiment, the robot queries the industrial computer whether it is in the obstacle avoidance state, if the current monitoring device is in the obstacle avoidance state, return to the obstacle avoidance, otherwise return to no obstacle avoidance.

[0097] Specifically, each monitoring device corresponds to a unique IP address according to different installation positions, and the IP address is used as the basis for the industrial computer to identify the monitoring device. Among them, the gigabit switch is selected to connect between the monitoring device and the industrial computer, and the data of multiple monitoring devices is sufficient to exceed 100M, so the gigabit switch is needed to ensure smooth network communication.

[0098] Specifically, the robot queries whether to avoid obstacles through the industrial computer, and the specific steps are as follows:

[0099] a, connect TCP server, make the host communicate with the industrial computer;

[0100] When requesting a new TCP connection, the industrial computer sends a small TCP packet (usually 40-60 bytes) to the host. A special SYN flag is set in this packet, indicating that it is a connection request. If the host receives the connection, it will calculate some connection parameters and send a TCP packet back to the industrial computer. The SYN and ACK flags in this packet are set, indicating that the connection request has been received. Finally, the industrial computer sends an acknowledgement message to the host, notifying it that the connection has been successfully established;

[0101] b, query whether the connection is successful, if the connection is successful, proceed to the next step, if not, continue to connect the industrial computer;

[0102] Specifically, the method for detecting whether the TCP connection is successful can include the following steps:

[0103] Use the ping command in the CMD environment to check. For example, ping server: start -- run -- input cmd -- enter -- input ping192.168.0.10 -- t -- enter (the specific IP address is determined according to the actual IP address) to check the return value. If there is a return value, it means that the network is smooth and the TCP connection is successful. If there is no return value, it may not be successful. If it is continuous, it means that the network is stable, and if there is a disconnection in the middle, it means that the network has a packet loss phenomenon.

[0104] c, start a thread to query whether to avoid obstacles;

[0105] d, query whether to avoid obstacles, query whether to avoid obstacles from the industrial computer of the robot, if avoiding obstacles, send an obstacle avoidance instruction to the action module, if no obstacle avoidance, continue to query and wait for action.

[0106] In addition, the embodiment of the application also provides a space active safety obstacle avoidance device based on a robot.

[0107] Reference Figure 6 , Figure 6 The function module diagram of the space active safety obstacle avoidance device based on a robot.

[0108] In this embodiment, the space active safety obstacle avoidance device based on a robot comprises:

[0109] The monitoring area generation module 10 is used to acquire device pose information of a plurality of monitoring devices corresponding to a target robot through the industrial computer, and determine a monitoring area corresponding to each monitoring device according to state information of the target robot and / or each device pose information.

[0110] The monitoring area combination module 20 is configured to combine the target monitoring area according to each monitoring area by the industrial computer.

[0111] The obstacle area judgment module 30 is configured to judge whether there is an obstacle area in the target monitoring area based on the point cloud information corresponding to the target monitoring area by the industrial computer.

[0112] The obstacle avoidance signal sending module 40 is configured to control the target robot to avoid obstacles when it is determined that there is an obstacle area in the target monitoring area by the industrial computer.

[0113] Further, the monitoring area generation module 10 specifically comprises:

[0114] The device pose acquisition unit is configured to acquire the pose of each monitoring device based on the installation position of each monitoring device and the monitoring angle by the industrial computer.

[0115] The monitoring area generation unit is configured to confirm the monitoring area corresponding to each monitoring device based on the pose of each monitoring device, and combine the target monitoring area by the industrial computer.

[0116] Further, the monitoring area combination module 20 specifically comprises:

[0117] The monitoring area combination unit is configured to combine the target monitoring area according to each monitoring area by the industrial computer.

[0118] Further, the obstacle area judgment module 30 specifically comprises:

[0119] The robot pose acquisition unit is configured to acquire the target robot pose information and the initial pose information of each monitoring device by the industrial computer.

[0120] The relative pose relationship unit is configured to calculate the relative pose relationship between the initial pose information and the target robot pose information by the industrial computer.

[0121] The point cloud information acquisition unit is configured to acquire the point cloud information scanned by each monitoring device by the industrial computer.

[0122] The point cloud information conversion unit is configured to convert the point cloud information scanned by each monitoring device into the point cloud information corresponding to the target robot as the point cloud information corresponding to the target monitoring area according to the relative pose relationship by the industrial computer.

[0123] The obstacle area judgment unit is configured to determine, by the industrial computer, whether the obstacle area exists in the target monitoring area.

[0124] Further, the obstacle avoidance signal sending module 40 specifically comprises:

[0125] The obstacle avoidance signal sending unit is configured to control the target robot to perform obstacle avoidance when it is determined by the industrial computer that the obstacle area exists in the target monitoring area.

[0126] Corresponding to each step in the above-mentioned method for robot-based active safety obstacle avoidance in space, each module in the above-mentioned device for robot-based active safety obstacle avoidance in space corresponds to the function and implementation process, which will not be described here.

[0127] In addition, the embodiment of the present application also provides a computer readable storage medium.

[0128] The computer readable storage medium of the present application stores an obstacle avoidance program, wherein when the robot-based active safety obstacle avoidance program is executed by the processor, the steps of the above-mentioned method for robot-based active safety obstacle avoidance in space are realized.

[0129] The method realized when the obstacle avoidance program is executed can refer to each embodiment of the method for robot-based active safety obstacle avoidance in space of the present application, which will not be described here.

[0130] It should be noted that in this paper, the term "including", "containing" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or system. Without more limitations, the element defined by the statement "including a" does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0131] The above-mentioned embodiment number of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0132] The application is operable with numerous general purpose or special purpose computing system environments or configurations. Examples of well- known computing systems, environments, and / or configurations that can be suitable for use with the application include personal computers, server computers, handheld or laptop devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0133] Those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disc) as described above, and includes a number of instructions for making a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device) execute the methods described in various embodiments of the present application.

[0134] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for active safety obstacle avoidance in space based on a robot, characterized in that, The method is applied to an industrial computer, multiple monitoring devices are installed at preset positions of a target robot, and the method comprises: The industrial computer acquires initial monitoring areas corresponding to the monitoring devices, adjusts the initial monitoring areas corresponding to the monitoring devices according to state information of the target robot, and determines monitoring areas corresponding to the monitoring devices; the industrial computer acquires a position and / or a moving speed of the target robot as the state information; The industrial computer combines the monitoring areas to generate a target monitoring area; The industrial computer determines whether an obstacle area exists in the target monitoring area based on point cloud information corresponding to the target monitoring area; When the industrial computer determines that the obstacle area exists in the target monitoring area, the industrial computer controls the target robot to avoid the obstacle.

2. A method for active safety obstacle avoidance in space based on a robot, characterized in that, The method is applied to an industrial computer, multiple monitoring devices are installed at preset positions of a target robot, and the method comprises: The industrial computer acquires installation positions and monitoring angles of the monitoring devices relative to the target robot as device pose information of the monitoring devices; The industrial computer determines monitoring areas corresponding to the monitoring devices based on the installation positions and the monitoring angles of the monitoring devices; the industrial computer acquires a position and / or a moving speed of the target robot as state information; and the industrial computer adjusts the monitoring areas of the monitoring devices according to the state information of the target robot; The industrial computer combines the monitoring areas to generate a target monitoring area; The industrial computer determines whether an obstacle area exists in the target monitoring area based on point cloud information corresponding to the target monitoring area; When the industrial computer determines that the obstacle area exists in the target monitoring area, the industrial computer controls the target robot to avoid the obstacle.

3. The obstacle avoidance method according to claim 1 or 2, characterized in that, The monitoring devices are devices capable of acquiring 3D point clouds.

4. The obstacle avoidance method according to claim 1 or 2, characterized in that, Before the industrial computer determines whether an obstacle area exists in the target monitoring area based on point cloud information corresponding to the target monitoring area, the industrial computer further comprises: The industrial computer acquires target robot pose information and initial pose information of the monitoring devices, and calculates a relative pose relationship between the initial pose information and the target robot pose information; The industrial computer acquires point cloud information scanned by the monitoring devices, and converts the point cloud information scanned by the monitoring devices into point cloud information corresponding to the target robot according to the relative pose relationship, as the point cloud information corresponding to the target monitoring area.

5. A robot-based space active safety obstacle avoidance device, characterized by, The space active safety obstacle avoidance device based on a robot is applied to an industrial computer, multiple monitoring devices are installed at preset positions of a target robot, and the space active safety obstacle avoidance device based on the robot comprises: The monitoring area generation module is configured to acquire, by the industrial computer, initial monitoring areas corresponding to the monitoring devices, adjust the initial monitoring areas corresponding to the monitoring devices according to state information of the target robot, and determine monitoring areas corresponding to the monitoring devices; the industrial computer acquires a position and / or a moving speed of the target robot as the state information; The monitoring area combination module is configured to combine, by the industrial computer, target monitoring areas according to the monitoring areas; The obstacle area judgment module is configured to judge, by the industrial computer, whether there is an obstacle area in the target monitoring area based on point cloud information corresponding to the target monitoring area; The obstacle avoidance signal sending module is configured to control, by the industrial computer, the target robot to avoid obstacles when it is determined that there is the obstacle area in the target monitoring area.

6. A robot-based space active safety obstacle avoidance device, characterized by, The robot-based space active safety obstacle avoidance device is applied to an industrial computer, a plurality of monitoring devices are installed at preset positions of a target robot, and the robot-based space active safety obstacle avoidance device is used to implement steps of the robot-based space active safety obstacle avoidance method in any one of claims 2-4.

7. A computer readable storage medium characterized in that, The computer readable storage medium stores a robot-based space active safety obstacle avoidance program, and when the robot-based space active safety obstacle avoidance program is executed by a processor, steps of the robot-based space active safety obstacle avoidance method in any one of claims 1-4 are implemented.

Images