CN117444984B - Manipulator control method and system for railway robot - Google Patents
Manipulator control method and system for railway robot Download PDFInfo
- Publication number
- CN117444984B CN117444984B CN202311757861.XA CN202311757861A CN117444984B CN 117444984 B CN117444984 B CN 117444984B CN 202311757861 A CN202311757861 A CN 202311757861A CN 117444984 B CN117444984 B CN 117444984B
- Authority
- CN
- China
- Prior art keywords
- unhooking
- control
- target
- degree
- freedom
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000012636 effector Substances 0.000 claims abstract description 38
- 238000009825 accumulation Methods 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 22
- 239000000463 material Substances 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000006073 displacement reaction Methods 0.000 claims description 13
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
The application provides a manipulator control method and a system for a railway robot, and relates to the technical field of manipulator control, wherein the method comprises the following steps: acquiring a manipulator degree of freedom node of the railway robot; a plurality of control modules that determine a job of the end effector; acquiring a plurality of degree of freedom intervals corresponding to a plurality of control modules; obtaining a unhooking dynamic index, and obtaining positioning information of a target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index; performing self-adaptive control on the plurality of control modules to obtain a plurality of groups of control parameters of the plurality of control modules; the railway robot is subjected to unhooking control, the technical problems that in the prior art, the unhooking position is dynamically changed due to differences in the shape and structure of the unhooking of the carriage, and poor operation control accuracy of the manipulator is caused due to vibration jolt of the carriage are solved, the manipulator control accuracy of the railway robot is improved, the operation efficiency is improved, and the collision risk is reduced are solved.
Description
Technical Field
The application relates to the technical field of manipulator control, in particular to a manipulator control method and system for a railway robot.
Background
Currently, the unhooking portions of trains in railway freight are all done manually and recorded. The manual unhooking work is complex, the work safety coefficient is low, safety accidents are easy to occur, along with the rapid development of artificial intelligence technology, the train unhooking robot is developed, the train unhooking robot carries out unhooking operation through a manipulator, but the unhooking position is dynamically changed due to the difference of the shape and the structure of a carriage unhooking, and the vibration jolt of the carriage causes poor operation control accuracy of the manipulator.
Disclosure of Invention
The application provides a manipulator control method and a manipulator control system for a railway robot, which are used for solving the technical problems that in the prior art, the shape and the structure of a coupler of a carriage are different, the vibration jolt of the carriage enables the coupler position to dynamically change, and the operation control accuracy of the manipulator is poor.
According to a first aspect of the present application, there is provided a robot arm control method for a railway robot, comprising: acquiring a manipulator degree of freedom node of the railway robot; determining a plurality of control modules of the operation of the end effector according to the manipulator degree of freedom nodes, wherein each control module corresponds to one degree of freedom node; acquiring a plurality of degree of freedom intervals corresponding to the plurality of control modules; identifying a target unhooking device according to the video acquisition device of the railway robot to obtain a unhooking dynamic index, and acquiring positioning information of the target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index; inputting the positioning information of the target unhooking into the end effector, and performing self-adaptive control on the plurality of control modules by taking the current positioning information of the end effector as an initial position and the target unhooking positioning information as an end position and taking the plurality of degree-of-freedom intervals as constraint conditions to obtain a plurality of groups of control parameters of the plurality of control modules; and carrying out unhooking control on the railway robot according to the plurality of groups of control parameters.
According to a second aspect of the present application, there is provided a robot arm control system for a railway robot, comprising: the degree-of-freedom node acquisition unit is used for acquiring the degree-of-freedom node of the manipulator of the railway robot; the control module determining unit is used for determining a plurality of control modules of the operation of the end effector according to the manipulator freedom degree nodes, wherein each control module corresponds to one freedom degree node; the degree of freedom interval acquisition unit is used for acquiring a plurality of degree of freedom intervals corresponding to the plurality of control modules; the target unhooking positioning unit is used for identifying a target unhooking according to a video acquisition device of the railway robot to obtain a unhooking dynamic index, and acquiring positioning information of the target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index; the control parameter acquisition unit is used for inputting the positioning information of the target hook into the end effector, taking the current positioning information of the end effector as an initial position, taking the positioning information of the target hook as an end position, and carrying out self-adaptive control on the control modules by taking the plurality of degree-of-freedom intervals as constraint conditions to obtain a plurality of groups of control parameters of the control modules; and the unhooking control unit is used for unhooking control of the railway robot according to the plurality of groups of control parameters.
According to one or more technical schemes adopted by the application, the beneficial effects which can be achieved are as follows:
acquiring a manipulator freedom degree node of the railway robot, determining a plurality of control modules of the operation of the end effector according to the manipulator freedom degree node, wherein each control module corresponds to one freedom degree node, acquiring a plurality of freedom degree intervals corresponding to the plurality of control modules, identifying a target unhooking according to a video acquisition device of the railway robot to obtain a unhooking dynamic index, acquiring positioning information of the target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index, inputting the positioning information of the target unhooking into the end effector, performing self-adaptive control on the plurality of control modules by taking the current positioning information of the end effector as an initial position and the positioning information of the target unhooking as an end position and taking the plurality of freedom degree intervals as constraint conditions, obtaining a plurality of groups of control parameters of the plurality of control modules, and performing unhooking control on the railway robot according to the plurality of groups of control parameters. Therefore, the target unhooking is subjected to unhooking dynamic index analysis, and then the adaptability optimization of the control parameters of the control modules is performed, so that the manipulator control accuracy of the railway robot is improved, the working efficiency is improved, and the technical effect of collision risk is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the present application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. The accompanying drawings, which form a part hereof, illustrate embodiments of the present application and, together with the description, serve to explain the present application and not to limit the application unduly, and to enable a person skilled in the art to make and use other drawings without the benefit of the present inventive subject matter.
Fig. 1 is a schematic flow chart of a manipulator control method for a railway robot according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a manipulator control system for a railway robot according to an embodiment of the present application.
Reference numerals illustrate: a degree-of-freedom node acquisition unit 11, a control module determination unit 12, a degree-of-freedom section acquisition unit 13, a target unhooking positioning unit 14, a control parameter acquisition unit 15, and a unhooking control unit 16.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, exemplary embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
The terminology used in the description is for the purpose of describing embodiments only and is not intended to be limiting of the application. As used in this specification, the singular terms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and/or "comprising," when used in this specification, specify the presence of steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other steps, operations, elements, components, and/or groups thereof.
Unless defined otherwise, all terms (including technical and scientific terms) used in this specification should have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. Terms, such as those defined in commonly used dictionaries, should not be interpreted in an idealized or overly formal sense unless expressly so defined herein. Like numbers refer to like elements throughout.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for presentation, analyzed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
First embodiment, fig. 1 is a diagram of a method for controlling a manipulator for a railway robot according to an embodiment of the present application, where the method includes:
acquiring a manipulator degree of freedom node of the railway robot;
the manipulator degree of freedom node of the railway robot is obtained, the railway robot is a robot for unhooking a train, the railway robot generally unhooks through the manipulator, the manipulator degree of freedom node is a joint of which the manipulator can freely move, the manipulator colloquially comprises a plurality of sections of mechanical arms, two adjacent sections of mechanical arms are connected through a movable joint, namely a node, and therefore the railway robot has a plurality of manipulator degree of freedom nodes, and the plurality of sections of mechanical arms can move to different positions and directions, so that the tail end of the mechanical arm reaches the target position to unhook. The manipulator degree of freedom nodes are determined by those skilled in the art in combination with the type of railway robot that is actually used, and are not limited in this regard.
And determining a plurality of control modules of the operation of the end effector according to the manipulator freedom degree nodes, wherein each control module corresponds to one freedom degree node.
And determining a plurality of control modules of the operation of the end effector according to the manipulator degree of freedom nodes, wherein each control module corresponds to one degree of freedom node, i.e. the number of the plurality of control modules is the same as the number of the manipulator degree of freedom nodes. The end effector is a device for performing control execution, which is connected to the degree of freedom node of the manipulator of the railway robot, and the plurality of control modules are used for a plurality of controllers for controlling the corresponding degree of freedom node.
Independent control of different parts of the manipulator can be achieved by dividing the degree of freedom node of the manipulator into a plurality of control modules, so that accurate control of the manipulator is achieved, the control flexibility of the manipulator is improved, and stable unhooking operation is guaranteed.
And acquiring a plurality of degree of freedom intervals corresponding to the plurality of control modules.
And acquiring a plurality of degree of freedom intervals corresponding to the plurality of control modules, wherein the degree of freedom intervals are controllable ranges of angles and displacements of the degree of freedom nodes corresponding to each control module, for example, the degree of freedom intervals can be rotated by 0 to 180 degrees, and the degree of freedom intervals are specifically determined by combining with reality.
And identifying the target unhooking according to the video acquisition device of the railway robot to obtain a unhooking dynamic index, and acquiring positioning information of the target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index.
The video acquisition device refers to intelligent cameras and other devices which are arranged on the railway robot and used for image shooting. The train unhooking means that the unvented carriages are separated, unhooking image acquisition is carried out according to the video acquisition device of the railway robot, the target unhooking is identified, unhooking dynamic indexes are obtained, the unhooking dynamic indexes are used for representing the vibration jolt degree of the carriages to be unhooked due to the motion relation, wheels, railway states and the like, the preset unhooking dynamic indexes are automatically set by the expert in the field in combination with actual experience, that is, if the unhooking dynamic indexes are greater than or equal to the preset unhooking dynamic indexes, the vibration jolt degree of the carriages is too high, the railway robot is controlled, unhooking failure is easily caused, and unhooking operation is not easy to carry out at this time. When the dynamic unhooking index is smaller than the preset unhooking dynamic index, the unhooking operation can be performed through the railway robot, the positioning information of the target unhooking is acquired at the moment, the target unhooking refers to a car coupler used for connecting the cars to be unhooked, and the existing positioning device can be installed on the car coupler to acquire the positioning information.
In a preferred embodiment, further comprising:
acquiring a first carriage and a second carriage to be unhooked according to a carriage operation scheduling center; acquiring preset unhooking images of the first carriage and the second carriage; transmitting the preset unhooking image to a video acquisition device of the railway robot for identification to obtain an image set of the target unhooking; and dynamically analyzing the image set of the target unhooking to obtain the unhooking dynamic index.
Specifically, the method for obtaining the unhooking dynamic index comprises the following steps: the carriage operation dispatching center is an existing system or platform for managing and dispatching carriage operation, can acquire and process relevant information of carriage dispatching through various sensors, communication equipment and control systems, is connected with the carriage operation dispatching center, and acquires a first carriage and a second carriage to be unhooked, wherein the first carriage and the second carriage are any two carriages connected through a coupler. The method comprises the steps of collecting a preset unhooking image between a first carriage and a second carriage, wherein the preset unhooking image refers to a correct unhooking image between the first carriage and the second carriage, which is collected and stored in advance by a person skilled in the art, and unhooking design between the first carriage and the second carriage can be displayed in the preset unhooking image, so that a railway robot can conveniently position unhooking targets. The preset unhooking images are transmitted to a video acquisition device of the railway robot for recognition, that is, the carriage operation dispatching center may have a plurality of trains, unhooking structures, shapes and the like of different trains, in order to prevent the recognition error of the target unhooking, the video acquisition device of the railway robot can perform continuous image acquisition in the visual field through the rotation direction, a plurality of images in the continuous image acquisition result of the image recognition technology in the prior art and the preset unhooking images are recognized and analyzed, when the images consistent with the preset unhooking images are recognized, the target unhooking is recognized, the video acquisition device is fixed to perform video acquisition, the image collection of the target unhooking is acquired, the accuracy of the unhooking image acquisition is ensured, and the accuracy of unhooking operation is ensured. Further dynamically analyzing the image set of the target unhooking, wherein the image set comprises multi-frame images under continuous acquisition time, identifying the unhooking position aiming at each frame of images, further analyzing the position change degree of the unhooking under the continuous acquisition time as the unhooking dynamic index, judging and executing unhooking control according to the unhooking dynamic index, and assisting in improving the unhooking control accuracy.
In a preferred embodiment, further comprising:
carrying out image frame identification on the image set of the target unhooking to obtain a plurality of continuous frames; respectively extracting edges of the target hook according to the plurality of continuous frames to obtain an edge coordinate set of each continuous frame; and carrying out coordinate change analysis according to the edge coordinate sets of the plurality of continuous frames to obtain the dynamic index of the unhooking.
The method for obtaining the dynamic index of the target unhooking by dynamically analyzing the image set of the target unhooking comprises the following steps: and carrying out image frame identification on the image set of the target hook, namely simply extracting the image set frame by utilizing the prior art, and separating continuous image frames to obtain a plurality of continuous frames. Performing edge extraction on the target hook according to the continuous frames to obtain an edge coordinate set of each continuous frame; the edge detection is an existing image feature extraction method, and the edge detection method includes, but is not limited to, sobel, canny, prewitt and other algorithms, and can be used for extracting edges of target hooks in a plurality of continuous frames according to any method of actual conditions to obtain an edge coordinate set of each continuous frame. According to the edge coordinate sets of the continuous frames, coordinate change analysis is performed, in short, the coordinates in the edge coordinate sets correspond to the edge coordinate sets of the continuous frames, the coordinates in the edge coordinate sets have a corresponding relation, only the coordinates in the same position of the edge of the target hook change due to vibration jolt of a carriage, therefore, only the coordinates in the edge coordinate sets need to be subjected to difference comparison, the deviation degree existing among the coordinates in the edge coordinate sets is obtained to serve as the dynamic index of the hook, dynamic analysis of the target hook is achieved, and further the hook picking control is judged and performed according to the dynamic index of the hook.
In a preferred embodiment, further comprising:
acquiring unhooking structure information and unhooking material information of the target unhooking; carrying out structural division on the target unhooking according to the unhooking structure information and the unhooking material information, and obtaining the dynamic influence of each component; dividing the region of the target hook according to the dynamic influence of each component to obtain a first component; and acquiring an edge coordinate set of the first component, and carrying out coordinate change analysis on the edge coordinate set of the first component to obtain the dynamic index of the unhooking.
The unhooking structure information and unhooking material information of the target unhooking are obtained, the unhooking structure information refers to the physical structure of the target unhooking, namely target unhooking structure components, such as a hook head, a hook body and a hook tail, the hook head comprises a hook tongue, a hook lock iron, a lock lifting pin and the like, the unhooking material information refers to manufacturing materials of the target unhooking, and the properties of different materials, such as different elastic modulus, density and the like, are different, such as steel materials with different specifications, and the materials of different components of the same unhooking may be different. Both the unhooking structure information and the unhooking material information are determined by those skilled in the art in combination with the actual situation. The target unhooking is structurally divided according to the unhooking structure information and the unhooking material information, in short, the unhooking structure information and the unhooking material information are used as classification standards, and an existing classification algorithm is utilized for structural division to divide a plurality of components.
The dynamic influence of each component is further obtained, namely the influence degree of each component on unhooking operation when dynamic jolt change occurs is analyzed, specifically, unhooking operation error records which are completely the same as unhooking material information of each component can be called through the prior art, the unhooking operation error records comprise edge coordinate change degree record values of each component, and then the correlation analysis is carried out on each component and unhooking operation errors by the existing correlation analysis method, such as gray correlation, by using the unhooking operation error records as a data base, and the correlation analysis result is used as the dynamic influence of each component.
And dividing the target hook into areas according to the dynamic influence of each component, namely dividing the component with consistent dynamic influence into one area to form a new component, and taking any new component as a first component. And extracting the edge coordinates of the first component corresponding to the plurality of continuous frames according to the edge coordinate sets of the plurality of continuous frames to form an edge coordinate set of the first component, carrying out coordinate change analysis on the edge coordinate set of the first component to obtain the deviation degree existing between the corresponding edge coordinates of the plurality of continuous frames, and then carrying out weighted calculation on the deviation degree according to the dynamic influence of the first component, wherein the weighted calculation result is used as the dynamic index of the unhooking, so that the accurate analysis of the dynamic index of the unhooking is realized, and the accuracy of the unhooking operation control of the railway robot is convenient to improve.
And inputting the positioning information of the target unhooking into the end effector, and performing self-adaptive control on the plurality of control modules by taking the current positioning information of the end effector as an initial position, the positioning information of the target unhooking as an end position and the plurality of degree-of-freedom intervals as constraint conditions to obtain a plurality of groups of control parameters of the plurality of control modules.
And inputting the positioning information of the target hook into the end effector, wherein the end effector is provided with an existing positioning device for positioning the end effector in real time, the current positioning information of the end effector is taken as an initial position, the positioning information of the target hook is taken as an end position, the plurality of control modules are adaptively controlled by taking the plurality of degree-of-freedom intervals as constraint conditions, and a plurality of groups of control parameters of the plurality of control modules are obtained.
In a preferred embodiment, further comprising:
taking the current positioning information of the end effector as an initial position, taking the target unhooking positioning information as an end position, taking the multiple degree of freedom intervals as constraint conditions of each control module, and inputting an adaptability optimizing model; and carrying out self-adaptive control on the plurality of control modules according to the fitness optimizing model to obtain a plurality of groups of control parameters of the plurality of control modules, wherein each control module corresponds to a group of control parameters, and each group of control parameters comprises a degree-of-freedom space angle vector and a space displacement vector.
In a preferred embodiment, further comprising:
acquiring unhooking obstacle characteristics according to the video acquisition device of the railway robot; inputting the unhooking obstacle characteristics into the fitness optimizing model to adaptively control the plurality of control modules, so as to obtain obstacle adaptive safety; when the obstacle self-adaptive safety degree meets the preset self-adaptive safety degree, acquiring control accumulation duration of the plurality of control modules; and minimizing the control accumulation duration as a convergence condition of the fitness optimizing model, and outputting a plurality of groups of control parameters of the plurality of control modules.
And taking the current positioning information of the end effector as an initial position, taking the target unhooking positioning information as an end position, taking the multiple degree-of-freedom intervals as constraint conditions of each control module, inputting an adaptive degree optimizing model which is a machine learning model in the prior art, and carrying out self-adaptive control on the multiple control modules according to the adaptive degree optimizing model to obtain multiple groups of control parameters of the multiple control modules, wherein each control module corresponds to one group of control parameters, each group of control parameters comprises a degree-of-freedom space angle vector and a space displacement vector, the degree-of-freedom space angle vector is the rotation angle of a degree-of-freedom node, and the space displacement vector is the displacement corresponding to the degree-of-freedom node.
Specifically, according to the video acquisition device of the railway robot, the unhooking obstacle feature is obtained, the unhooking obstacle feature is an obstacle position coordinate which can obstruct the operation of the manipulator of the railway robot, for example, the manipulator needs to bypass a carriage to perform unhooking operation, and the carriage coordinate is the unhooking obstacle feature. Specifically, the position coordinates of other targets, such as a carriage, except for the target unhooking, can be extracted from the image acquired by the video acquisition device through the existing target recognition algorithm, so as to obtain unhooking obstacle features.
The unhooking obstacle characteristics are input into the fitness optimizing model to carry out self-adaptive control on the plurality of control modules to obtain obstacle self-adaptive safety, namely, the current positioning information of the end effector is taken as an initial position, the target unhooking positioning information is taken as an end position, the plurality of degree-of-freedom intervals are taken as constraint conditions of each control module, the end effector can be ensured to move from the initial position to the end position as long as the movable range of a degree-of-freedom node corresponding to each module meets the plurality of degree-of-freedom intervals, a plurality of groups of degree-of-freedom space angle vectors and space displacement vectors meeting the constraint conditions of the plurality of control modules can be searched, the position cross identification is carried out on the plurality of groups of degree-of-freedom space angle vectors and space displacement vectors and the unhooking obstacle characteristics through the fitness optimizing model, whether the target unhooking obstacle positioning information coincides with the unhooking obstacle characteristics when the plurality of groups of degree-of-freedom space angle vectors moves is judged, namely, collision can be calculated, and the minimum distance between the unhooking obstacle characteristics and preset safety ratio of the preset safety is taken as the practical self-adaptive safety by combining the fitness optimizing model.
The preset self-adaptive safety degree is obtained by a person skilled in the art, when the obstacle self-adaptive safety degree meets the preset self-adaptive safety degree, the control accumulation duration of a plurality of groups of free degree space angle vectors and space displacement vectors corresponding to the space displacement vectors meeting the preset self-adaptive safety degree is obtained, the control accumulation duration is minimized to serve as a convergence condition of the adaptive degree optimizing model, namely, a plurality of groups of free degree space angle vectors and space displacement vectors corresponding to the minimum control accumulation duration are output to serve as a plurality of groups of control parameters of the plurality of control modules. Therefore, optimizing of control parameters is achieved, operation accuracy and operation efficiency are improved, and collision risk is reduced.
In a preferred embodiment, further comprising:
acquiring a control state memory bank of the plurality of control modules, wherein the control state memory bank holds memory control parameters of which the control accumulation duration of the plurality of control modules is smaller than a preset control accumulation duration and memory control parameters of which the obstacle collision frequency of the plurality of control modules is smaller than a preset obstacle collision frequency; and connecting the control state memory library with the fitness optimizing model, and optimizing in the control state memory library to obtain a plurality of groups of control parameters of the plurality of control modules.
The method comprises the steps of obtaining a control state memory library of the plurality of control modules, wherein the control state memory library is reserved with memory control parameters of which the control accumulation duration of the plurality of control modules is smaller than a preset control accumulation duration and memory control parameters of which the obstacle collision frequency of the plurality of control modules is smaller than a preset obstacle collision frequency, and the control state memory library is extracted based on the existing historical control record, namely, the historical control parameters of the railway robot during historical unhooking operation are extracted, and the historical control accumulation duration corresponding to the historical control parameters is extracted. The preset control accumulation duration is combined with actual setting by a person skilled in the art, and according to the historical control accumulation duration, historical control parameters with accumulation duration smaller than the preset control accumulation duration are extracted to form a control state memory bank of a plurality of control modules. And connecting the control state memory library with the fitness optimizing model, and optimizing in the control state memory library to obtain a plurality of groups of control parameters of the plurality of control modules.
In popular terms, when the current positioning information of the end effector is taken as an initial position, the target hook positioning information is taken as an end position, the multiple degree of freedom intervals are taken as constraint conditions of each control module, an adaptive degree optimizing model is input, and when the multiple control modules are subjected to adaptive control, multiple groups of degree of freedom space angle vectors and space displacement vectors meeting the constraint conditions are screened from a control state memory bank, and then control accumulation duration of the multiple control modules is extracted through the control state memory bank, so that adaptive degree optimizing is performed, and optimizing efficiency is improved.
And carrying out unhooking control on the railway robot according to the plurality of groups of control parameters.
And finally, taking the plurality of groups of control parameters as the control parameters of the railway robot to perform unhooking control, so as to ensure the accuracy of unhooking control.
Based on the above analysis, the one or more technical solutions provided in the present application can achieve the following beneficial effects:
acquiring a manipulator freedom degree node of the railway robot, determining a plurality of control modules of the operation of the end effector according to the manipulator freedom degree node, wherein each control module corresponds to one freedom degree node, acquiring a plurality of freedom degree intervals corresponding to the plurality of control modules, identifying a target unhooking according to a video acquisition device of the railway robot to obtain a unhooking dynamic index, acquiring positioning information of the target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index, inputting the positioning information of the target unhooking into the end effector, performing self-adaptive control on the plurality of control modules by taking the current positioning information of the end effector as an initial position and the positioning information of the target unhooking as an end position and taking the plurality of freedom degree intervals as constraint conditions, obtaining a plurality of groups of control parameters of the plurality of control modules, and performing unhooking control on the railway robot according to the plurality of groups of control parameters. Therefore, the target unhooking is subjected to unhooking dynamic index analysis, and then the adaptability optimization of the control parameters of the control modules is performed, so that the manipulator control accuracy of the railway robot is improved, the working efficiency is improved, and the technical effect of collision risk is reduced.
In a second embodiment, based on the same inventive concept as the manipulator control method for a railway robot in the previous embodiment, as shown in fig. 2, the present application further provides a manipulator control system for a railway robot, the system comprising:
and a degree-of-freedom node acquiring unit 11, wherein the degree-of-freedom node acquiring unit 11 is used for acquiring a manipulator degree-of-freedom node of the railway robot.
And a control module determining unit 12, wherein the control module determining unit 12 is configured to determine a plurality of control modules of the operation of the end effector according to the degrees of freedom nodes of the manipulator, and each control module corresponds to one degree of freedom node.
And a degree-of-freedom section acquiring unit 13, where the degree-of-freedom section acquiring unit 13 is configured to acquire a plurality of degree-of-freedom sections corresponding to the plurality of control modules.
The target unhooking positioning unit 14, the target unhooking positioning unit 14 is used for identifying a target unhooking according to the video acquisition device of the railway robot to obtain a unhooking dynamic index, and when the unhooking dynamic index is smaller than a preset unhooking dynamic index, the positioning information of the target unhooking is obtained.
The control parameter obtaining unit 15 is configured to input positioning information of the target hook into the end effector, take current positioning information of the end effector as an initial position, take the target hook positioning information as an end position, and perform adaptive control on the plurality of control modules with the plurality of degree-of-freedom intervals as constraint conditions, so as to obtain a plurality of groups of control parameters of the plurality of control modules.
And the unhooking control unit 16 is used for unhooking control of the railway robot according to the plurality of groups of control parameters by the unhooking control unit 16.
Further, the target hook positioning unit 14 further includes:
and acquiring a first carriage and a second carriage to be unhooked according to the carriage operation scheduling center.
And acquiring preset unhooking images of the first carriage and the second carriage.
And transmitting the preset unhooking image to a video acquisition device of the railway robot for identification to obtain an image set of the target unhooking.
And dynamically analyzing the image set of the target unhooking to obtain the unhooking dynamic index.
Further, the target hook positioning unit 14 further includes:
and carrying out image frame recognition on the image set of the target hook to obtain a plurality of continuous frames.
And respectively carrying out edge extraction on the target hook according to the plurality of continuous frames to obtain an edge coordinate set of each continuous frame.
And carrying out coordinate change analysis according to the edge coordinate sets of the plurality of continuous frames to obtain the dynamic index of the unhooking.
Further, the target hook positioning unit 14 further includes:
and acquiring unhooking structure information and unhooking material information of the target unhooking.
And carrying out structural division on the target unhooking according to the unhooking structure information and the unhooking material information, and obtaining the dynamic influence of each component.
And dividing the target hook into areas according to the dynamic influence of each component to obtain a first component.
And acquiring an edge coordinate set of the first component, and carrying out coordinate change analysis on the edge coordinate set of the first component to obtain the dynamic index of the unhooking.
Further, the control parameter obtaining unit 15 further includes:
and taking the current positioning information of the end effector as an initial position, taking the target hook positioning information as an end position, taking the multiple degree of freedom intervals as constraint conditions of each control module, and inputting an adaptability optimizing model.
And carrying out self-adaptive control on the plurality of control modules according to the fitness optimizing model to obtain a plurality of groups of control parameters of the plurality of control modules, wherein each control module corresponds to a group of control parameters, and each group of control parameters comprises a degree-of-freedom space angle vector and a space displacement vector.
Further, the control parameter obtaining unit 15 further includes:
and acquiring unhooking obstacle characteristics according to the video acquisition device of the railway robot.
And inputting the unhooking obstacle characteristics into the fitness optimizing model to perform self-adaptive control on the plurality of control modules, so as to obtain the obstacle self-adaptive safety degree.
And when the obstacle self-adaptive safety degree meets the preset self-adaptive safety degree, acquiring control accumulation duration of the plurality of control modules.
And minimizing the control accumulation duration as a convergence condition of the fitness optimizing model, and outputting a plurality of groups of control parameters of the plurality of control modules.
Further, the control parameter obtaining unit 15 further includes:
and acquiring a control state memory bank of the plurality of control modules, wherein the control state memory bank holds memory control parameters of which the control accumulation duration of the plurality of control modules is smaller than a preset control accumulation duration and memory control parameters of which the obstacle collision frequency of the plurality of control modules is smaller than a preset obstacle collision frequency.
And connecting the control state memory library with the fitness optimizing model, and optimizing in the control state memory library to obtain a plurality of groups of control parameters of the plurality of control modules.
The specific example of the manipulator control method for a railway robot in the first embodiment described above is also applicable to the manipulator control system for a railway robot of the present embodiment, and the manipulator control system for a railway robot of the present embodiment will be clearly known to those skilled in the art from the foregoing detailed description of the manipulator control method for a railway robot, so that the detailed description thereof will not be repeated for the sake of brevity.
It should be understood that the various forms of flow shown above, reordered, added, or deleted steps may be used, as long as the desired results of the presently disclosed technology are achieved, and are not limited herein.
Note that the above is only a preferred embodiment of the present application and the technical principle applied. Those skilled in the art will appreciate that the present application is not limited to the particular embodiments described herein, but is capable of numerous obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the present application. Therefore, while the present application has been described in connection with the above embodiments, the present application is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the present application, the scope of which is defined by the scope of the appended claims.
Claims (7)
1. A method for controlling a manipulator for a railway robot, the method comprising:
acquiring a manipulator degree of freedom node of the railway robot;
determining a plurality of control modules of the operation of the end effector according to the manipulator degree of freedom nodes, wherein each control module corresponds to one degree of freedom node;
acquiring a plurality of degree of freedom intervals corresponding to the plurality of control modules;
identifying a target unhooking device according to the video acquisition device of the railway robot to obtain a unhooking dynamic index, and acquiring positioning information of the target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index;
inputting the positioning information of the target unhooking into the end effector, and performing self-adaptive control on the plurality of control modules by taking the current positioning information of the end effector as an initial position and the target unhooking positioning information as an end position and taking the plurality of degree-of-freedom intervals as constraint conditions to obtain a plurality of groups of control parameters of the plurality of control modules;
unhooking control is carried out on the railway robot according to the plurality of groups of control parameters;
the method for identifying the target unhooking according to the video acquisition device of the railway robot to obtain the unhooking dynamic index comprises the following steps:
acquiring a first carriage and a second carriage to be unhooked according to a carriage operation scheduling center;
acquiring preset unhooking images of the first carriage and the second carriage;
transmitting the preset unhooking image to a video acquisition device of the railway robot for identification to obtain an image set of the target unhooking;
and dynamically analyzing the image set of the target unhooking to obtain the unhooking dynamic index.
2. The method of claim 1, wherein dynamically analyzing the set of images of the target hook to obtain the hook dynamic indicator comprises:
carrying out image frame identification on the image set of the target unhooking to obtain a plurality of continuous frames;
respectively extracting edges of the target hook according to the plurality of continuous frames to obtain an edge coordinate set of each continuous frame;
and carrying out coordinate change analysis according to the edge coordinate sets of the plurality of continuous frames to obtain the dynamic index of the unhooking.
3. The method of claim 2, wherein said performing a coordinate change analysis based on said plurality of consecutive frames' edge coordinate sets to obtain said unhooking dynamic indicator comprises:
acquiring unhooking structure information and unhooking material information of the target unhooking;
carrying out structural division on the target unhooking according to the unhooking structure information and the unhooking material information, and obtaining the dynamic influence of each component;
dividing the region of the target hook according to the dynamic influence of each component to obtain a first component;
and acquiring an edge coordinate set of the first component, and carrying out coordinate change analysis on the edge coordinate set of the first component to obtain the dynamic index of the unhooking.
4. The method of claim 1, wherein the deriving the plurality of sets of control parameters for the plurality of control modules comprises:
taking the current positioning information of the end effector as an initial position, taking the target unhooking positioning information as an end position, taking the multiple degree of freedom intervals as constraint conditions of each control module, and inputting an adaptability optimizing model;
and carrying out self-adaptive control on the plurality of control modules according to the fitness optimizing model to obtain a plurality of groups of control parameters of the plurality of control modules, wherein each control module corresponds to a group of control parameters, and each group of control parameters comprises a degree-of-freedom space angle vector and a space displacement vector.
5. The method of claim 4, wherein the adaptively controlling the plurality of control modules according to the fitness optimization model comprises:
acquiring unhooking obstacle characteristics according to the video acquisition device of the railway robot;
inputting the unhooking obstacle characteristics into the fitness optimizing model to adaptively control the plurality of control modules, so as to obtain obstacle adaptive safety;
when the obstacle self-adaptive safety degree meets the preset self-adaptive safety degree, acquiring control accumulation duration of the plurality of control modules;
and minimizing the control accumulation duration as a convergence condition of the fitness optimizing model, and outputting a plurality of groups of control parameters of the plurality of control modules.
6. The method of claim 4, wherein the adaptively controlling the plurality of control modules according to the fitness optimizing model further comprises:
acquiring a control state memory bank of the plurality of control modules, wherein the control state memory bank holds memory control parameters of which the control accumulation duration of the plurality of control modules is smaller than a preset control accumulation duration and memory control parameters of which the obstacle collision frequency of the plurality of control modules is smaller than a preset obstacle collision frequency;
and connecting the control state memory library with the fitness optimizing model, and optimizing in the control state memory library to obtain a plurality of groups of control parameters of the plurality of control modules.
7. A manipulator control system for a railway robot, characterized by the steps for performing the method of any of claims 1 to 6, the system comprising:
the degree-of-freedom node acquisition unit is used for acquiring the degree-of-freedom node of the manipulator of the railway robot;
the control module determining unit is used for determining a plurality of control modules of the operation of the end effector according to the manipulator freedom degree nodes, wherein each control module corresponds to one freedom degree node;
the degree of freedom interval acquisition unit is used for acquiring a plurality of degree of freedom intervals corresponding to the plurality of control modules;
the target unhooking positioning unit is used for identifying a target unhooking according to a video acquisition device of the railway robot to obtain a unhooking dynamic index, and acquiring positioning information of the target unhooking when the unhooking dynamic index is smaller than a preset unhooking dynamic index;
the control parameter acquisition unit is used for inputting the positioning information of the target hook into the end effector, taking the current positioning information of the end effector as an initial position, taking the positioning information of the target hook as an end position, and carrying out self-adaptive control on the control modules by taking the plurality of degree-of-freedom intervals as constraint conditions to obtain a plurality of groups of control parameters of the control modules;
and the unhooking control unit is used for unhooking control of the railway robot according to the plurality of groups of control parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311757861.XA CN117444984B (en) | 2023-12-20 | 2023-12-20 | Manipulator control method and system for railway robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311757861.XA CN117444984B (en) | 2023-12-20 | 2023-12-20 | Manipulator control method and system for railway robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117444984A CN117444984A (en) | 2024-01-26 |
| CN117444984B true CN117444984B (en) | 2024-03-08 |
Family
ID=89585807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311757861.XA Active CN117444984B (en) | 2023-12-20 | 2023-12-20 | Manipulator control method and system for railway robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117444984B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117923191B (en) * | 2024-03-21 | 2024-07-23 | 沈阳奇辉机器人应用技术有限公司 | Intelligent control method and system for unloading of car dumper based on unhooking robot |
| CN118493403B (en) * | 2024-07-16 | 2024-10-01 | 中科航宇(北京)自动化工程技术有限公司 | Unhooking robot control method and system based on depth visual recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5531337A (en) * | 1995-05-30 | 1996-07-02 | Inco Limited | Automated decoupler for rail cars |
| CN101346269A (en) * | 2005-12-23 | 2009-01-14 | 通用电气公司 | Coupler, apparatus, system and method for determining whether a train enginge is coupled to a rail car or other engine |
| CN108122447A (en) * | 2018-01-11 | 2018-06-05 | 中铁第四勘察设计院集团有限公司 | A kind of subway hitch malfunction simulation system based on VR technologies |
| JP2020082199A (en) * | 2018-11-15 | 2020-06-04 | トヨタ自動車株式会社 | Control device |
| CN211543548U (en) * | 2019-11-26 | 2020-09-22 | 中冶南方（武汉）自动化有限公司 | Automatic unhooking system of robot for train coupler |
| CN114973159A (en) * | 2022-05-16 | 2022-08-30 | 北京轨道交通技术装备集团有限公司 | Method, system and device for detecting coupling state of car coupler |
| CN217413994U (en) * | 2022-05-12 | 2022-09-13 | 四川泰锋智能科技股份有限公司 | Supplementary couple equipment of plucking of rail vehicle and control system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11358615B2 (en) * | 2002-06-04 | 2022-06-14 | Ge Global Sourcing Llc | System and method for determining vehicle orientation in a vehicle consist |
-
2023
- 2023-12-20 CN CN202311757861.XA patent/CN117444984B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5531337A (en) * | 1995-05-30 | 1996-07-02 | Inco Limited | Automated decoupler for rail cars |
| CN101346269A (en) * | 2005-12-23 | 2009-01-14 | 通用电气公司 | Coupler, apparatus, system and method for determining whether a train enginge is coupled to a rail car or other engine |
| CN108122447A (en) * | 2018-01-11 | 2018-06-05 | 中铁第四勘察设计院集团有限公司 | A kind of subway hitch malfunction simulation system based on VR technologies |
| JP2020082199A (en) * | 2018-11-15 | 2020-06-04 | トヨタ自動車株式会社 | Control device |
| CN211543548U (en) * | 2019-11-26 | 2020-09-22 | 中冶南方（武汉）自动化有限公司 | Automatic unhooking system of robot for train coupler |
| CN217413994U (en) * | 2022-05-12 | 2022-09-13 | 四川泰锋智能科技股份有限公司 | Supplementary couple equipment of plucking of rail vehicle and control system |
| CN114973159A (en) * | 2022-05-16 | 2022-08-30 | 北京轨道交通技术装备集团有限公司 | Method, system and device for detecting coupling state of car coupler |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117444984A (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117444984B (en) | Manipulator control method and system for railway robot | |
| CN109606263B (en) | Method for monitoring blind spot of monitoring vehicle and blind spot monitor using the same | |
| CN111709974A (en) | Human body tracking method and device based on RGB-D image | |
| US11504846B2 (en) | Robot teaching system based on image segmentation and surface electromyography and robot teaching method thereof | |
| CN108055501A (en) | A kind of target detection and the video monitoring system and method for tracking | |
| US20120259462A1 (en) | Information processing apparatus, control method thereof and storage medium | |
| CN112441055B (en) | Train unhooking robot unhooking control method | |
| CN106003043A (en) | Obstacle avoidance method and obstacle avoidance system of mechanical arm | |
| CN106197452A (en) | A kind of visual pattern processing equipment and system | |
| JP2020204804A (en) | Image recognition device | |
| CN105468033A (en) | Control method for medical suspension alarm automatic obstacle avoidance based on multi-camera machine vision | |
| CN112330702A (en) | Point cloud completion method and device, electronic equipment and storage medium | |
| CN111739333B (en) | Empty parking space identification method | |
| KR20200076267A (en) | Gesture Recognition Method and Processing System using Skeleton Length Information | |
| CN109079792A (en) | A kind of target based on multirobot surrounds and seize method and system | |
| CN109986605A (en) | A kind of intelligence automatically tracks robot system and method | |
| CN114926422B (en) | Method and system for detecting passenger flow of getting on and off vehicles | |
| CN105759650A (en) | Method used for intelligent robot system to achieve real-time face tracking | |
| CN112936282A (en) | Method and system for improving motion sensing control accuracy of industrial robot | |
| CN106444753B (en) | Human body situation based on artificial neural network judges intelligent follower method | |
| CN115812646A (en) | Method for analyzing fish behaviors in fishway | |
| CN118605538B (en) | Multi-source-based target data collaborative processing method and system | |
| JP2003067755A (en) | Road white line recognition device | |
| CN117732827B (en) | Battery shell cleaning line feeding and discharging control system and method based on robot | |
| Yang et al. | Online pantograph-catenary contact point detection in complicated background based on multiple strategies |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |