Positioning and guiding method for mobile operation robot

Abstract

The present disclosure provides a positioning and guiding method for a mobile operating robot, which includes: S102, obtaining environmental data information; S104, sampling and processing the environmental data information obtained by the laser radar to optimize, construct a global grid map of a large scene, and store it in a server; S106, according to the point cloud data of the mobile chassis at this moment collected by the laser radar at the current moment, using the global grid map in the server to perform feature matching of the posture information of the mobile chassis, so as to achieve global positioning of the mobile chassis; S108, optimizing the trajectory of the mobile chassis of the mobile operating robot from the starting point to the point to be operated; S110, according to the optimized trajectory, controlling the mobile chassis of the mobile operating robot to move to the point to be operated; and S112, using a visual mechanism to scan the large scene to obtain point cloud data of the large scene; identifying the object to be operated through the point cloud data of the large scene obtained by the visual mechanism, and controlling the mechanical arm to operate the object to be operated.

Description

Technical Field

[0001] The present invention relates to a positioning and guiding method for a mobile operating robot, and belongs to the technical field of robots. Background Art

[0002] With the continuous development of Internet of Things and artificial intelligence technologies, the positioning of mobile robots plays an important role. It is the most critical issue in many industrial applications, such as logistics sorting, unmanned driving, industrial AGV and other fields. Global positioning and posture tracking are the main problems faced by mobile robot positioning.

[0003] Global positioning mainly involves the mobile robot scanning and building a global map of its environment through machine vision technology, thereby realizing the positioning of the mobile robot. The mobile robot needs some sensor information to complete the global positioning task, that is, the information detected by the sensors that perceive the surrounding environment. The positioning sensors used by mobile robots are mainly laser radar and visual cameras. When the mobile robot performs global positioning, it will mainly face the following three difficulties: ① The position of the robot at the previous moment is unknown; ② When repositioning or closed-loop detection, the working environment will undergo various changes, including changes in lighting, ground roughness, and obstacles, which will cause certain errors; ③ When building a map, the complexity of the information detected by the sensor will bring certain difficulties to positioning.

[0004] In the prior art, there is a method of manually building a model, namely machine learning, to achieve global positioning of a mobile robot, and use GPS signals to provide a global position. However, the machine learning method has low accuracy when building a map. And GPS will fail in indoor environments or confined spaces.

[0005] In recent years, the global positioning of mobile robots has been achieved by methods based on visual information. Patent application "CN110533722A" proposes a robot rapid repositioning method and system based on a visual dictionary. The principle is to compare the visual image with the key frames stored in the visual map constructed by the sensor, find the most similar frame, and then perform feature matching between the two images. Finally, the position information of the mobile robot is obtained to achieve global positioning of the mobile robot.

[0006] In the research of mobile robot posture tracking, robust positioning and high-precision positioning of target points have become its main challenges. In the patent application "CN112068547A", a robot positioning method, device and robot based on AMCL are proposed. It mainly uses laser data and map files. The AMCL algorithm will optimize the particle distribution of the predicted initial particle group to obtain a more concentrated particle distribution, and then use the laser data and map files to realize the real-time positioning and posture correction of the robot.

[0007] However, under the existing technical conditions and working environment, the accuracy that can be achieved by the positioning methods in the existing technology still cannot meet certain specific occasions. Especially in industrial scenarios, the positioning of mobile operating robots must reach millimeter-level accuracy to ensure the safety and reliability of industrial production. Summary of the invention

[0008] In order to solve one of the above technical problems, the present disclosure provides a positioning and guiding method for a mobile operating robot.

[0009] According to one aspect of the present disclosure, a method for positioning and guiding a mobile operating robot is provided, wherein the mobile operating robot comprises a mobile chassis and a mechanical arm mounted on the mobile chassis, wherein a laser radar is arranged on the mobile chassis, and a visual mechanism is arranged on the mechanical arm; the method for positioning and guiding the mobile operating robot comprises:

[0010] S102, using a laser radar to sample data of a large scene where the mobile chassis is located to obtain environmental data information;

[0011] S104, sampling and processing the environmental data information obtained by the laser radar to optimize the global grid map of the large scene, and store it in the server;

[0012] S106, performing feature matching of the position and posture information of the mobile chassis using the global grid map in the server according to the point cloud data of the mobile chassis at this moment collected by the laser radar at the current moment, so as to realize the global positioning of the mobile chassis;

[0013] S108, optimizing the trajectory of the mobile chassis of the mobile operation robot from the starting point to the point to be operated;

[0014] S110, controlling the mobile chassis of the mobile operation robot to move to the waiting operation point according to the optimized trajectory;

[0015] S112, using a visual mechanism to scan the large scene to obtain point cloud data of the large scene; identifying an object to be operated through the point cloud data of the large scene obtained by the visual mechanism, and controlling the robotic arm to operate the object to be operated.

[0016] According to the mobile operating robot positioning and guiding method of at least one embodiment of the present disclosure, in S102, machine learning or autonomous learning is adopted to use the laser radar on the mobile chassis to collect environmental data information of the working scene of the mobile operating robot.

[0017] According to the mobile operating robot positioning and guidance method of at least one embodiment of the present disclosure, in S104, sliding windows with different resolutions are used to slide downsample the environmental data information, and a plurality of global grid maps with different resolutions are obtained; the plurality of global grid maps with different resolutions are combined in a triangle shape in order of resolution from high to low to construct a global grid map of a large scene, and stored in a server.

[0018] According to the positioning and guiding method of a mobile operating robot according to at least one embodiment of the present disclosure, S106 includes:

[0019] The position of the mobile robot at the last moment detected by the laser radar and vision mechanism and the position of the mobile operating robot detected by the laser radar and vision mechanism at the current moment , thereby estimating the probability that each grid map in the global grid map of each resolution is occupied by the end of the laser beam.

[0020] According to the mobile operating robot positioning and guiding method of at least one embodiment of the present disclosure, S106 further includes:

[0021] Obtain the data difference of the position transformation of the mobile robot at two adjacent moments in a grid with the lowest resolution in the global grid map ;in, ;in,

[0022] ; represents the meaning of right The derivative of

[0023] ; represents the meaning of right Derivation;

[0024] ; represents the meaning of right The derivation of Indicates The coordinates of the end points of the laser beam;

[0025] . BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings illustrate exemplary embodiments of the present disclosure and together with the description serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0027] Figure 1 It is a structural schematic diagram of a positioning and guiding method for a mobile operating robot according to an embodiment of the present disclosure.

[0028] Figure 2 It is a schematic structural diagram of a mobile operating robot according to one embodiment of the present disclosure.

[0029] The specific reference numerals in the figure are:

[0030] 200 Mobile Manipulator Robot

[0031] 210 Mobile chassis

[0032] 220 Robotic arm. DETAILED DESCRIPTION

[0033] The present disclosure is further described in detail below in conjunction with the accompanying drawings and implementations. It is understood that the specific implementations described herein are only used to explain the relevant content, rather than to limit the present disclosure. It should also be noted that, for ease of description, only the parts related to the present disclosure are shown in the accompanying drawings.

[0034] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure can be combined with each other. The technical solution of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0035] Unless otherwise specified, the exemplary embodiments / embodiments shown will be understood as providing exemplary features of various details of some ways in which the technical concept of the present disclosure can be implemented in practice. Therefore, unless otherwise specified, the features of the various embodiments / embodiments can be combined, separated, interchanged and / or rearranged without departing from the technical concept of the present disclosure.

[0036] The use of cross-hatching and / or shading in the accompanying drawings is generally used to make the boundaries between adjacent components clear. As such, unless otherwise specified, the presence or absence of cross-hatching or shading does not convey or indicate any preference or requirement for the specific materials, material properties, dimensions, proportions, commonalities between the components shown, and / or any other characteristics, attributes, properties, etc. of the components. In addition, in the accompanying drawings, the sizes and relative sizes of the components may be exaggerated for clarity and / or descriptive purposes. When the exemplary embodiments can be implemented differently, the specific process sequence can be performed in a different order than described. For example, two successively described processes can be performed substantially simultaneously or in an order opposite to the described order. In addition, the same figure numbers represent the same components.

[0037] When a component is referred to as being "on" or "over," "connected to," or "coupled to" another component, the component may be directly on, directly connected to, or directly coupled to the other component, or intervening components may be present. However, when a component is referred to as being "directly on," "directly connected to," or "directly coupled to" another component, there are no intervening components. For this purpose, the term "connected" may refer to a physical connection, an electrical connection, etc., with or without intervening components.

[0038] For descriptive purposes, the present disclosure may use spatially relative terms such as "under," "beneath," "under," "down," "over," "upper," "above," "higher," and "side (e.g., as in "sidewall")," to describe the relationship of one component to another (other) component as shown in the accompanying drawings. The spatially relative terms are intended to encompass different orientations of the device in use, operation, and / or manufacture in addition to the orientation depicted in the accompanying drawings. For example, if the device in the accompanying drawings is turned over, components described as "under" or "beneath" other components or features would subsequently be positioned "over" the other components or features. Thus, the exemplary term "under" can encompass both the "above" and "below" orientations. Furthermore, the device may be otherwise oriented (e.g., rotated 90 degrees or at other orientations), and the spatially relative descriptors used herein should be interpreted accordingly.

[0039] The terms used here are for the purpose of describing specific embodiments, and are not intended to be restrictive. As used here, unless the context clearly indicates otherwise, the singular forms "one (kind, person)" and "said (the)" are also intended to include plural forms. In addition, when the terms "comprise" and / or "include" and their variations are used in this specification, it is explained that there are stated features, integral bodies, steps, operations, parts, assemblies and / or their groups, but it is not excluded that there are or add one or more other features, integral bodies, steps, operations, parts, assemblies and / or their groups. It should also be noted that, as used here, the terms "substantially", "approximately" and other similar terms are used as approximate terms and not as degree terms, so that they are used to explain the inherent deviations of the measured values, calculated values ​​and / or the values ​​provided that will be recognized by those of ordinary skill in the art.

[0040] Figure 1 It is a structural schematic diagram of a positioning and guiding method for a mobile operating robot according to an embodiment of the present disclosure.

[0041] like Figure 1 As shown, the mobile operating robot used in the mobile operating robot positioning and guiding method of the present invention includes a mobile chassis and a mechanical arm installed on the mobile chassis.

[0042] In one embodiment, the mobile chassis may include a driving wheel and a steering wheel; the driving wheel is installed in the middle of the mobile chassis to provide driving force for traveling; there are multiple steering wheels, and multiple steering wheels are installed around the driving wheel to provide steering driving force. More preferably, there are two driving wheels and four steering wheels. Both the driving wheel and the rotating wheel adopt McRae wheels, so that the omnidirectional movement function can be realized more flexibly and conveniently.

[0043] The mobile chassis is provided with a laser radar to construct a map and perform global positioning of the mobile chassis through the laser radar. Moreover, the laser radar can also be used to detect obstacles around the mobile operating robot during operation.

[0044] The robotic arm may be a multi-degree-of-freedom robotic arm, for example, a six-degree-of-freedom or seven-degree-of-freedom robotic arm, and a visual mechanism is provided on the multi-degree-of-freedom robotic arm. In the present disclosure, the visual mechanism may include structures such as a depth camera and a distance sensor, so as to sense the positional relationship between the object to be operated and the end effector of the robotic arm through the visual mechanism, so as to ensure that the end effector of the robotic arm can reliably operate the target object. In a preferred embodiment, the end effector can perform grabbing and placing operations on the object to be operated.

[0045] Of course, those skilled in the art should know that the end effector mechanism disclosed herein can be replaced according to different work requirements, such as gripping cylindrical objects with a claw, sucking up large flat objects with a suction cup, drilling holes in objects to be processed, and so on.

[0046] In one embodiment, the mobile chassis and the robotic arm each include a controller, that is, the mobile chassis and the robotic arm can be controlled by their respective controllers and perform corresponding actions. Moreover, the controller of the mobile chassis can perform trajectory planning for the mobile chassis, and correspondingly, the controller of the robotic arm can perform trajectory planning for the actions of the robotic arm, and these trajectory planning data are all sent to the server, and the server decides whether to act.

[0047] In one embodiment, the mobile chassis is also provided with an encoder using odometer information, and the data information of the encoder is used to indicate the position of the mobile operation robot at the current moment. , Indicates the horizontal and vertical coordinates. Indicates that the mobile operation robot is at the current moment The laser radar data indicates the relative position between the mobile robot and the obstacle at the current moment. , is the straight-line distance between the mobile operating robot and the obstacle at the current moment, is the line between the mobile robot and the obstacle at the current moment and The angle of the axis, therefore, in the present disclosure, the global position of the mobile chassis can be achieved through the absolute position information obtained by the encoder and the relative position information obtained by the laser radar.

[0048] In the present disclosure, based on the structure of the above-mentioned mobile operating robot, the positioning and guiding method of the mobile operating robot includes: S102, using a laser radar to sample the data of the large scene where the mobile chassis is located to obtain environmental data information; S104, sampling, processing and optimizing the environmental data information obtained by the laser radar, constructing a global grid map of the large scene, and storing it in a server; S106, according to the point cloud data of the mobile chassis at this moment collected by the laser radar at the current moment, using the global grid map in the server to perform feature matching of the posture information of the mobile chassis, and realizing the global positioning of the mobile chassis; S108, optimizing the trajectory of the mobile chassis of the mobile operating robot from the starting point to the point to be operated; S110, according to the optimized trajectory, controlling the mobile chassis of the mobile operating robot to move to the point to be operated; and S112, using a visual mechanism to scan the large scene to obtain point cloud data of the large scene; identifying the object to be operated through the point cloud data of the large scene obtained by the visual mechanism, and controlling the robotic arm to operate the object to be operated.

[0049] The above steps will be described in detail below.

[0050] In S102, a laser radar on a mobile chassis is used to collect environmental data information of the working scene of the mobile operation robot by machine learning or autonomous learning. At this time, the collected annular data information can be uploaded to a server, that is, uploaded to a computer, and a global grid map is generated by the server.

[0051] Specifically, in S104, sliding windows of different resolutions are used to perform sliding downsampling on the environmental data information, and a plurality of global grid maps of different resolutions are obtained; the plurality of global grid maps of different resolutions are combined in the order of resolution from high to low and in the shape of a triangle to construct a global grid map of a large scene, and the global grid map is stored in the server.

[0052] For example, first, a sliding window with a resolution of 4×4 is used to perform sliding downsampling on the original global map to obtain a global grid map of a first resolution; then, a sliding window with a resolution of 3×3 is used to perform sliding downsampling on the original global map to obtain a global grid map of a second resolution; then, a sliding window with a resolution of 2×2 is used to perform sliding downsampling on the original global map to obtain a global grid map of a third resolution; finally, a sliding window with a resolution of 1×1 is used to perform sliding downsampling on the original global map to obtain a global grid map of a fourth resolution.

[0053] Then, the global grid maps of the four resolutions are combined in the order of resolution from high to low and in the shape of triangles to construct a global grid map of the large scene and store it in the server.

[0054] Those skilled in the art should know that when a mobile operation robot is performing an operation, the positioning accuracy directly determines the operation accuracy of the mobile operation robot. Based on this, the focus of the present disclosure is on the accurate global positioning of the mobile operation robot.

[0055] Specifically, S106 includes:

[0056] The position of the mobile robot at the last moment detected by the laser radar and / or vision mechanism and the position of the mobile operating robot detected by the laser radar and vision mechanism at the current moment , thereby estimating the probability that each grid map in the global grid map of each resolution is occupied by the end of the laser beam. Specifically, a least square error function can be constructed to estimate the probability that each grid map in the above is occupied by the end of the laser beam.

[0057] Among them, the least squares error function is ,in represents the coordinates of the end point of the i-th laser beam after the position of the mobile operation robot is transformed between two adjacent moments; Indicates the The probability that a global grid map is occupied by the end of the laser beam; the larger the probability, the higher the probability. The greater the probability that the grid map is occupied by the end of the laser beam, the more likely the mobile robot is in the constructed global map at this moment. The greater the probability of being in the grid map; n is a natural number.

[0058] Obtain the data difference of the position transformation of the mobile robot at two adjacent moments in a grid with the lowest resolution in the global grid map ;in, ;in, Represents the coordinates of the end point of the i-th laser beam.

[0059] ; represents the meaning of right The derivative of

[0060] ; represents the meaning of right Derivation;

[0061] ; represents the meaning of right The derivation of Indicates The coordinates of the end points of the laser beam;

[0062] .

[0063] The position of the mobile operating robot at the current moment is determined by the position of the mobile operating robot at the previous moment and the data difference.

[0064] Initialize an initial particle swarm representing the mobile position of the mobile operation robot, wherein each particle in the initial particle swarm includes the position of the mobile operation robot at the initial moment and a grid map of each resolution. The particle swarm includes a plurality of particles, each of which includes a grid map and the corresponding position of the mobile operation robot. Initializing the particle swarm is to eliminate the original positioning error caused by the mobile operation robot initially entering the workspace, and to eliminate the error that affects the construction of the global map.

[0065] According to the environmental information detected by the laser radar and / or visual mechanism at different times, the particle swarms at different times are obtained; wherein the particles in the particle swarms at different times represent the positions of the mobile operation robot at different times. The particle swarms represent the global maps constructed by the mobile operation robot at different times.

[0066] More preferably, in the particle swarm at different times, the weight of each particle is determined according to the degree of matching between each particle in the particle swarm and its corresponding grid map; each particle in the particle swarm is sorted according to its weight, and the particle with the largest weight is used as the target particle, and the target particle is selected by random selection for particles with the same weight. The larger the weight, the closer the position of the mobile operation robot in the global map constructed by itself is to the position of the mobile operation robot in the actual working scene. The random selection method is used to select the target particle for particles with the same weight in order to increase the randomness of the selection and avoid the situation where the same particle is always selected.

[0067] In the global grid map with different resolutions, the position data difference of the mobile robot at two adjacent moments is used to calculate the position of the robot. , expand the particle swarm at different times and obtain the expanded particle swarm corresponding to the global grid map of different resolutions. Correspondingly, the weight of each particle in the expanded particle swarm will also be different. When the effective particles in the expanded particle swarm are lower than the set standard value, resampling is required. Remove the particles with lower weights in the particle swarm and retain the particles with higher weights. The resampling process is to replace the particles with lower weights with particles with higher weights. Effectively improve the mapping effect of the mobile operation robot and the positioning accuracy of the mobile operation robot.

[0068] In S108, the starting point and the point to be operated of the mobile operation robot are set, and the trajectory of the mobile operation robot from the starting point to the target point is repeatedly performed in the simulation window. The stability of the mobile operation robot is judged. Fixed roadblock points and movable roadblock points are manually added in the simulation window to perform motion simulation of the mobile operation robot, and the flexibility and applicability of the mobile operation robot are tested, thereby confirming a feasible trajectory from the starting point to the point to be operated of the mobile operation robot.

[0069] When the trajectory is confirmed, the mobile operating robot is controlled to move from the starting point to the point to be operated; during the movement of the mobile operating robot, obstacles around the mobile operating robot are detected in real time through the laser radar, and a movement trajectory that avoids the obstacles is planned.

[0070] In the present disclosure, in S112, the three-dimensional position of the object to be operated in the working scene of the robot arm is obtained according to the pre-stored features of the object to be operated.

[0071] For example, after the mobile chassis moves to the operating position, an image of the object to be operated can be obtained through a depth camera arranged on the robotic arm; contour feature points of the object to be operated are obtained from the image, and the contour feature points are matched with target feature points pre-stored in the image processing unit, and the coordinates of the object to be operated are confirmed; the current working position is determined according to the coordinates of the object to be operated; the motion path is determined according to the current position of the end effector of the robotic arm and the current working position; the movement of the robotic arm is controlled according to the motion path, and the operation on the object to be operated is performed.

[0072] The mobile operating robot positioning and guidance method disclosed in the present invention can solve the problem of low positioning accuracy caused by most influencing factors, and can be applied in large scenes to achieve high-precision visual guidance positioning by visually identifying the position of the object to be operated.

[0073] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment / method or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments / methods or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments / methods or examples described in this specification and the features of the different embodiments / methods or examples, unless they are contradictory.

[0074] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0075] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present disclosure, and are not intended to limit the scope of the present disclosure. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present disclosure.

Claims

1. A positioning and guiding method for a mobile operating robot, wherein the mobile operating robot comprises a mobile chassis and a mechanical arm mounted on the mobile chassis, wherein a laser radar is arranged on the mobile chassis, and a visual mechanism is arranged on the mechanical arm; It is characterized in that The mobile operation robot positioning and guiding method comprises: S102, using a laser radar to sample data of a large scene where the mobile chassis is located to obtain environmental data information; S104, sampling and processing the environmental data information obtained by the laser radar to optimize the global grid map of the large scene, and store it in the server; S106, performing feature matching of the position and posture information of the mobile chassis using the global grid map in the server according to the point cloud data of the mobile chassis at this moment collected by the laser radar at the current moment, so as to realize the global positioning of the mobile chassis; S108, optimizing the trajectory of the mobile chassis of the mobile operation robot from the starting point to the point to be operated; S110, controlling the mobile chassis of the mobile operation robot to move to the waiting operation point according to the optimized trajectory; S112, using a visual mechanism to scan the large scene to obtain point cloud data of the large scene; identifying an object to be operated through the point cloud data of the large scene obtained by the visual mechanism, and controlling the robotic arm to operate the object to be operated; In S104, sliding windows with different resolutions are used to perform sliding downsampling on the environmental data information, and a plurality of global grid maps with different resolutions are obtained; the plurality of global grid maps with different resolutions are combined in a triangle shape in order of resolution from high to low to construct a global grid map of a large scene, and the global grid map is stored in the server; S106 includes: according to the position of the mobile operation robot at the last moment detected by the laser radar and the visual mechanism and the position of the mobile robot detected by the laser radar and vision mechanism at the current moment , thereby estimating the probability that each grid map in the global grid map of each resolution is occupied by the end of the laser beam; and obtaining the data difference of the position transformation of the mobile operation robot at two adjacent moments in a grid with the lowest resolution in the global grid map ;in, ;in, ; represents the meaning of right The derivative of ; represents the meaning of right Derivation; ; represents the meaning of right The derivation of Indicates The coordinates of the end points of the laser beam; 。 2. The method for positioning and guiding a mobile operating robot according to claim 1, It is characterized in that In S102, machine learning or autonomous learning is used to collect environmental data information of the working scene of the mobile operation robot using a laser radar on the mobile chassis.

Images