CN110864692A - Pose determination method of heading machine - Google Patents
Pose determination method of heading machine Download PDFInfo
- Publication number
- CN110864692A CN110864692A CN201911198011.4A CN201911198011A CN110864692A CN 110864692 A CN110864692 A CN 110864692A CN 201911198011 A CN201911198011 A CN 201911198011A CN 110864692 A CN110864692 A CN 110864692A
- Authority
- CN
- China
- Prior art keywords
- layer
- neural network
- network model
- convolutional neural
- data
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Navigation (AREA)
Abstract
The application discloses a position and posture determining method of a heading machine, which comprises the following steps: establishing a convolutional neural network model; training the convolutional neural network model to obtain a trained convolutional neural network model; acquiring advancing data of the development machine; and inputting the heading machine advancing data into the trained convolutional neural network model for processing to obtain final pose data. The position and pose determining method of the heading machine is scientific and reasonable in design, high in calculating speed and high in accuracy of a calculation result, and can well meet the requirements of practical application.
Description
Technical Field
The application relates to the technical field of heading machines, in particular to a pose determining method of a heading machine.
Background
In the prior art, the pose determination of the development machine mainly relates to the following methods:
guidance and positioning based on total station
The total station is called as a total station type electronic tacheometer, which is a measuring instrument capable of simultaneously carrying out angle (horizontal angle and vertical angle) measurement, distance measurement and data processing and formed by combining mechanical, optical and electronic elements. The basic function of the system is to acquire space point coordinates through a laser ranging sensor and 2 angular displacement sensors. The guiding technology based on the total station instrument is used for guiding the shield tunneling machine during tunneling for many years. Similar to the guiding of a shield tunneling machine, when the total station is used for guiding a cantilever tunneling machine, a plurality of prisms are required to be arranged on a tunneling machine body to serve as auxiliary detection feature points, and the space coordinates of the prisms on the tunneling machine body are respectively detected to calculate the pose of the tunneling machine body in a total station coordinate system. In order to establish a link between data measured by the total station and a roadway design axis, a rear-view prism is usually required to assist in determining a measurement coordinate system of the total station. The patent proposes that a tunneling machine head pose measurement system is established by utilizing a laser power-driven total station, a vehicle body yaw angle sensor, a double-shaft tilt angle sensor, an oil cylinder stroke sensor and the like. The measuring principle is that a total station is arranged on the wall of a roadway and used as a datum point, the total station measures the space position coordinates of a machine body in a geodetic coordinate system, a yaw angle sensor detects the yaw angle of the machine body, an inclination angle sensor detects the roll angle and the pitch angle of the machine body, an oil cylinder stroke sensor detects the space position of a cutting head relative to the machine body, and the space position coordinates of the cutting head in the geodetic coordinate system are measured on the basis.
The total station is higher in detection precision, but has the following problems that (1) the total station can only detect the coordinates of 1 point at the same moment, and the spatial coordinates of a plurality of points which are discretely distributed at the same moment are required to be detected for detecting the posture of the machine body of the heading machine, so that the total station is more suitable for static pose detection of the heading machine. (2) The automatic identification capability of the total station to the prism in the underground light environment is to be verified.
Gyroscope-based guiding and positioning principle
The operating principle of the gyroscope is that the gyroscope rotating at high speed can keep the axis orientation of the gyroscope unchanged. The gyroscope guides and positions the carrier by forming an inertial navigation system with the accelerometer. The inertial navigation technology is based on Newton's law of mechanics, the motion acceleration of the carrier in an inertial reference system is measured by using an accelerometer, the position of the carrier is calculated through time integral operation, and the position is transformed into a navigation coordinate system established by a gyroscope, so that the speed, the yaw angle, the position information and the like of the carrier in the navigation coordinate system can be obtained.
At present, a strapdown inertial navigation system is researched and used for unmanned driving and operation of a heading machine. In the research, an inertial navigation system consisting of a gyroscope and an accelerometer obtains acceleration signals and angular velocity signals of a vehicle body in three-axis directions, real-time position information of the heading machine vehicle body is obtained through navigation calculation, real-time course, pitch angle and roll angle of the vehicle body are obtained from the real-time position information of the vehicle body, and stretching and rotating amount of a mechanical arm are obtained from a displacement sensor signal, and the stretching and rotating amount and the rotating amount jointly determine attitude information of the heading machine. The attitude information of the heading machine is subjected to coordinate transformation to generate a real-time control deviation value, and the real-time control deviation value is fed back to the driving and controlling system, so that the attitude adjustment of the heading machine is realized, and the heading machine is driven to advance and cut according to a preset track. Inertial navigation systems can provide position, velocity, heading, and attitude angle data. Because the navigation information is generated by time integration, the positioning error is increased along with the time, therefore, when the navigation system is used for long-range continuous navigation, the inertial navigation system is required to be corrected at regular time by adopting instructions, terrain matching, GPS and the like so as to obtain continuous and accurate position parameters; (2) a long initial alignment time is required; (3) the equipment cost is high.
Electronic compass based guiding and positioning principle
The compass type sensor relies on a geomagnetic field for angle detection, such as an electronic compass, and is rigidly connected with the heading machine body, so that the heading direction of the heading machine axis is obtained by comparing the included angle between the heading machine body axis and the north pole of the geomagnetic field, and the heading machine attitude detection is completed together with pitch angle and roll angle information provided by an inclinometer.
The compass sensor is simple in principle and easy to form a system, but because the underground space of a coal mine is narrow and small, electromechanical equipment is relatively concentrated, particularly, the power of mining and transporting equipment is large, the load is unstable, the underground electromagnetic interference is serious, the structure of a rock stratum where a roadway is located is complex and changeable, the geomagnetic environment of the roadway is also complex and changeable, the electronic compass is used for measuring the earth magnetic field, and if magnetic fields except the earth magnetic field exist in the using environment and the magnetic fields cannot be effectively shielded, the compass sensor is difficult to use. Therefore, the technical difficulty lies in how to inhibit the influence of the complex electromagnetic field environment in the roadway on the detection process. Furthermore, electronic compass-based guidance technologies generally only give directional information and do not provide spatial location information.
Guiding and positioning principle based on laser guide instrument
For years, laser paying-off has been the most reliable method for roadway driving guidance and is still widely used globally. The position of the laser is determined by the measuring staff. The laser pointing direction is determined by a set of measuring points measured and positioned by geodetic personnel with a theodolite. The laser beam provides the center line and the waist line of the tunnel construction, and has higher precision, stability and reliability, therefore, research provides an automatic directional positioning method of the heading machine taking the guide laser as the reference, which integrates a laser guide instrument and a laser range finder for pointing and ranging, a light angle measuring instrument is arranged on the body of the heading machine, the reference axis of the light angle measuring instrument is parallel to the reference axis of the body, and the difference value of the horizontal angle and the pitch angle between the body of the heading machine and the guide laser beam is measured by receiving the guide laser; the electronic gyroscope on the machine body can directly measure parameters of a horizontal angle and a pitch angle of the machine body of the heading machine, a connection is established between the optical angle measuring instrument and a roadway reference axis, vector parameters of the roadway reference axis are derived, and absolute coordinate values of the current space of the heading machine can be obtained through a polar coordinate calculation method according to the distance between a measuring point and a reference point. The method also has the problem that whether the laser can be reliably received and tracked by the on-site optical goniometer.
Guiding and positioning principle based on vision measurement
The vision measurement refers to a technique for measuring the position and posture of a target based on image vision information obtained by a camera. In terms of application modes, the method is divided into 2 types of monocular vision measurement and multi-ocular vision measurement (mainly binocular vision). When the binocular vision measurement technology is used for guiding and positioning the development machine, a binocular vision sensor is rigidly connected with a laser direction indicator in a stereoscopic vision mode, the space coordinates of relevant characteristic points on the development machine body in an ideal roadway coordinate system can be directly detected, the space pose of the machine body relative to the direction laser is calculated, the rotation angle and the pitch angle of a cantilever relative to the machine body can be measured by detecting the displacement of a cantilever rotation oil cylinder and a pitch oil cylinder, the space position of a cutting head relative to the machine body can be calculated, the space position data of the cutting head relative to the direction laser is fused with the space pose data of the machine body relative to the direction laser, and the space position of the cutting head relative to the direction laser can.
The visual measurement technology is used for automatic guiding and positioning of the development machine, has the advantages of real time, non-contact, rich acquired information and the like, and the difficulty lies in how to overcome the influence of severe working conditions (such as dust, water mist, illumination conditions and the like) of a working surface on the detection precision.
The accuracy has direct influence on the forming accuracy of the roadway in the automatic cutting technology. Considering the factors such as the control precision and the severe working condition of the cantilever type tunneling machine, a larger deviation is usually generated in the execution link of cutting operation, so that the automatic positioning detection precision of the cantilever type tunneling machine needs to reach centimeter level, and the detection precision of the attitude and the heading can reach the boundary precision of the roadway section which is possibly required by the specification only when the detection precision reaches the angle classification.
The reference signal transmission medium of navigation technology based on photoelectric technology includes laser (such as point laser, line laser and total station), infrared and visible light, and features that the navigation system is divided into
Two parts are as follows: one part is used as a detection and signal device and fixed in a roadway reference; the other part is arranged on the body of the cantilever type heading machine as a signal transmitting device and moves along with the body, or vice versa. The fixed unit uses the calibrated laser direction indicator light beam as a reference to acquire the space position posture of the moving unit, namely the cantilever type tunneling machine body, and has the advantages of mature technology, high precision, low cost and the like, and the existing problems are as follows: environmental adaptability including attenuation of dust to visible light, absorption of water mist to infrared light, shielding caused by narrow space and the like; moving the reference forwards in stages and calibrating the reference again; the increase in distance degrades the detection resolution and detection accuracy.
In recent years, the research of the inertial navigation technology for the navigation of the cantilever type heading machine becomes a hotspot. In consideration of the characteristic of poor long-term precision of the inertial navigation technology and the centimeter-level positioning requirement of the cantilever type tunneling machine, when the inertial navigation technology is used for navigation positioning of the cantilever type tunneling machine, the positioning precision is greatly insufficient.
Generally, the pose determining method of the heading machine in the prior art is not high in precision and cannot meet the requirements of practical application, and a pose determining method with higher precision is urgently needed to be developed.
Disclosure of Invention
The application aims to provide a position and posture determining method of a heading machine. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to an aspect of an embodiment of the present application, there is provided a pose determination method for a heading machine, including:
establishing a convolutional neural network model;
training the convolutional neural network model to obtain a trained convolutional neural network model;
acquiring advancing data of the development machine;
and inputting the heading machine advancing data into the trained convolutional neural network model for processing to obtain final pose data.
Further, the convolutional neural network model comprises an input layer, an output layer and a hidden layer positioned between the input layer and the output layer.
Further, the input layer includes a plurality of first nodes; the hidden layer comprises a plurality of second nodes; the output layer includes a plurality of third nodes; the hidden layer is of a three-dimensional structure and is divided into a plurality of planes which are arranged at intervals along the direction from the input layer to the output layer, the second nodes are respectively positioned on the planes, the first node is connected with a plurality of second nodes positioned on one plane which is closest to the input layer, the third node is connected with a plurality of second nodes positioned on one plane which is closest to the output layer, the second nodes positioned on each plane are connected with each other, and the second nodes positioned on every two adjacent planes are connected along the arrangement direction of the planes, so that at least one second node in the hidden layer has at least six different data transmission directions in the arrangement direction of other second nodes positioned on the same plane and the planes.
Further, the hidden layer comprises a convolution layer, a pooling layer and a full-connection layer which are connected in sequence.
Further, the convolutional layer includes convolution kernels of size 3x3, with a step size of 1.
Further, the pooling layer employs a global average pooling function or a global maximum pooling function.
Further, the fully-connected layer adopts a sigmoid function or a tanh function; wherein:
the sigmoid function is defined by the formula s (x) ═ 1+ (e)x)-1]-1；
the tan h function is defined by the formula
Further, the heading machine travel data includes: inertial navigation data, odometer data and laser ranging data.
According to another aspect of the embodiments of the present application, there is provided a pose determination apparatus of a heading machine, including:
the building module is used for building a convolutional neural network model;
the training module is used for training the convolutional neural network model to obtain the trained convolutional neural network model;
the acquisition module is used for acquiring the advancing data of the development machine;
and the processing module is used for inputting the heading machine advancing data into the trained convolutional neural network model for processing to obtain final pose data.
According to another aspect of embodiments of the present application, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program which is executed by a processor to implement the pose determination method of a heading machine.
The technical scheme provided by one aspect of the embodiment of the application can have the following beneficial effects:
the position and orientation determining method of the heading machine, provided by the embodiment of the application, is scientific and reasonable in design, high in calculating speed and high in accuracy of a calculation result, and can well meet the requirements of practical application.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application, or may be learned by the practice of the embodiments. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 shows a flowchart of a pose determination method of a heading machine according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As shown in fig. 1, an embodiment of the present application provides a position and orientation determination method for a heading machine, including:
and S1, establishing a convolutional neural network model.
And S2, training the convolutional neural network model to obtain the trained convolutional neural network model.
S3, acquiring heading machine advancing data; the heading machine travel data includes inertial navigation data, odometer data, and laser ranging data, which are acquired by respective sensors.
And S4, inputting the heading machine advancing data into the trained convolutional neural network model for processing to obtain final pose data.
In some embodiments, the convolutional neural network model includes an input layer, an output layer, and a hidden layer between the input layer and the output layer.
In some embodiments, the input layer includes a plurality of first nodes; the hidden layer comprises a plurality of second nodes; the output layer includes a plurality of third nodes; the hidden layer is of a three-dimensional structure and is divided into a plurality of planes which are arranged at intervals along the direction from the input layer to the output layer, the second nodes are respectively positioned on the planes, the first node is connected with a plurality of second nodes positioned on one plane which is closest to the input layer, the third node is connected with a plurality of second nodes positioned on one plane which is closest to the output layer, the second nodes positioned on each plane are connected with each other, and the second nodes positioned on every two adjacent planes are connected along the arrangement direction of the planes, so that at least one second node in the hidden layer has at least six different data transmission directions in the arrangement direction of other second nodes positioned on the same plane and the planes.
In some embodiments, the hidden layer comprises a convolutional layer, a pooling layer, and a fully-connected layer connected in sequence.
In some embodiments, the convolutional layer comprises convolution kernels of size 3x3 with a step size of 1.
In some embodiments, the pooling layer employs a global average pooling function or a global maximum pooling function.
In some embodiments, the fully-connected layer employs a sigmoid function or a tanh function.
The sigmoid function is defined by the formula s (x) ═ 1+ (e)x)-1]-1。
the tan h function is defined by the formula
The embodiment also provides a position and posture determining device of the heading machine, which comprises:
the building module is used for building a convolutional neural network model;
the training module is used for training the convolutional neural network model to obtain the trained convolutional neural network model;
the acquisition module is used for acquiring the advancing data of the development machine;
and the processing module is used for inputting the heading machine advancing data into the trained convolutional neural network model for processing to obtain final pose data.
The present embodiment also provides a non-transitory computer-readable storage medium having stored thereon a computer program which is executed by a processor to implement the heading machine pose determination method.
It should be noted that:
the term "module" is not intended to be limited to a particular physical form. Depending on the particular application, a module may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same component. There may or may not be clear boundaries between the various modules.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. In addition, this application is not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and any descriptions of specific languages are provided above to disclose the best modes of the present application.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the application, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: this application is intended to cover such departures from the present disclosure as come within known or customary practice in the art to which this invention pertains. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the creation apparatus of a virtual machine according to embodiments of the present application. The present application may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The above-mentioned embodiments only express the embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A position and orientation determination method of a heading machine is characterized by comprising the following steps:
establishing a convolutional neural network model;
training the convolutional neural network model to obtain a trained convolutional neural network model;
acquiring advancing data of the development machine;
and inputting the heading machine advancing data into the trained convolutional neural network model for processing to obtain final pose data.
2. The method of claim 1, wherein the convolutional neural network model comprises an input layer, an output layer, and a hidden layer between the input layer and the output layer.
3. The method of claim 2, wherein the input layer comprises a plurality of first nodes; the hidden layer comprises a plurality of second nodes; the output layer includes a plurality of third nodes; the hidden layer is of a three-dimensional structure and is divided into a plurality of planes which are arranged at intervals along the direction from the input layer to the output layer, the second nodes are respectively positioned on the planes, the first node is connected with a plurality of second nodes positioned on one plane which is closest to the input layer, the third node is connected with a plurality of second nodes positioned on one plane which is closest to the output layer, the second nodes positioned on each plane are connected with each other, and the second nodes positioned on every two adjacent planes are connected along the arrangement direction of the planes, so that at least one second node in the hidden layer has at least six different data transmission directions in the arrangement direction of other second nodes positioned on the same plane and the planes.
4. The method of claim 2, wherein the hidden layer comprises a convolutional layer, a pooling layer, and a fully-connected layer connected in sequence.
5. The method of claim 4, wherein the convolutional layer comprises convolutional kernels of size 3x3 with a step size of 1.
6. The method of claim 4, wherein the pooling layer employs a global average pooling function or a global maximum pooling function.
7. The method of claim 4, wherein the fully-connected layer employs a sigmoid function or a tanh function; wherein:
the sigmoid function is defined by the formula s (x) ═ 1+ (e)x)-1]-1；
the tan h function is defined by the formula
8. The method of claim 1, wherein the heading machine travel data comprises: inertial navigation data, odometer data and laser ranging data.
9. A position and orientation determination device of a heading machine, characterized by comprising:
the building module is used for building a convolutional neural network model;
the training module is used for training the convolutional neural network model to obtain the trained convolutional neural network model;
the acquisition module is used for acquiring the advancing data of the development machine;
and the processing module is used for inputting the heading machine advancing data into the trained convolutional neural network model for processing to obtain final pose data.
10. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor to implement the pose determination method of a heading machine according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911198011.4A CN110864692A (en) | 2019-11-29 | 2019-11-29 | Pose determination method of heading machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911198011.4A CN110864692A (en) | 2019-11-29 | 2019-11-29 | Pose determination method of heading machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110864692A true CN110864692A (en) | 2020-03-06 |
Family
ID=69657681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911198011.4A Pending CN110864692A (en) | 2019-11-29 | 2019-11-29 | Pose determination method of heading machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110864692A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112304285A (en) * | 2020-11-03 | 2021-02-02 | 中国煤炭科工集团太原研究院有限公司 | Attitude detection method and system for cantilever type heading machine cutting head |
| CN112392498A (en) * | 2020-11-12 | 2021-02-23 | 三一重型装备有限公司 | Control method and device for cutting part of heading machine |
| CN112525158A (en) * | 2020-11-16 | 2021-03-19 | 江苏集萃智能光电系统研究所有限公司 | Double-shield six-degree-of-freedom measurement method and system based on monocular vision system |
| CN112556649A (en) * | 2020-11-30 | 2021-03-26 | 徐州徐工挖掘机械有限公司 | Method and device for correcting dip angle of excavator during dip angle measurement and dip angle measuring instrument |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170262962A1 (en) * | 2016-03-11 | 2017-09-14 | Qualcomm Incorporated | Systems and methods for normalizing an image |
| CN109630154A (en) * | 2019-01-24 | 2019-04-16 | 华能西藏雅鲁藏布江水电开发投资有限公司 | A kind of development machine people and remote mobile terminal command system for tunnel piercing |
| CN110045598A (en) * | 2019-04-10 | 2019-07-23 | 中国矿业大学(北京) | A kind of boom-type roadheader underground travel path tracking and controlling method |
| CN110486081A (en) * | 2019-08-06 | 2019-11-22 | 精英数智科技股份有限公司 | A kind of development machine operation safety monitoring method, system, equipment and storage medium |
-
2019
- 2019-11-29 CN CN201911198011.4A patent/CN110864692A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170262962A1 (en) * | 2016-03-11 | 2017-09-14 | Qualcomm Incorporated | Systems and methods for normalizing an image |
| CN109630154A (en) * | 2019-01-24 | 2019-04-16 | 华能西藏雅鲁藏布江水电开发投资有限公司 | A kind of development machine people and remote mobile terminal command system for tunnel piercing |
| CN110045598A (en) * | 2019-04-10 | 2019-07-23 | 中国矿业大学(北京) | A kind of boom-type roadheader underground travel path tracking and controlling method |
| CN110486081A (en) * | 2019-08-06 | 2019-11-22 | 精英数智科技股份有限公司 | A kind of development machine operation safety monitoring method, system, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 葛垚等: "基于 CNN 与 SVDD的掘进机智能监测系统设计", 《传感器与微系统》 * |
| 赵铎: "基于深度学习的机器人抓取位置检测", 《中国优秀硕士学位论文全文数据库 工程科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112304285A (en) * | 2020-11-03 | 2021-02-02 | 中国煤炭科工集团太原研究院有限公司 | Attitude detection method and system for cantilever type heading machine cutting head |
| CN112392498A (en) * | 2020-11-12 | 2021-02-23 | 三一重型装备有限公司 | Control method and device for cutting part of heading machine |
| CN112392498B (en) * | 2020-11-12 | 2022-12-16 | 三一重型装备有限公司 | Control method and device for cutting part of heading machine |
| CN112525158A (en) * | 2020-11-16 | 2021-03-19 | 江苏集萃智能光电系统研究所有限公司 | Double-shield six-degree-of-freedom measurement method and system based on monocular vision system |
| CN112556649A (en) * | 2020-11-30 | 2021-03-26 | 徐州徐工挖掘机械有限公司 | Method and device for correcting dip angle of excavator during dip angle measurement and dip angle measuring instrument |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111156998B (en) | Mobile robot positioning method based on RGB-D camera and IMU information fusion | |
| CN110864692A (en) | Pose determination method of heading machine | |
| US8494225B2 (en) | Navigation method and aparatus | |
| CN109991636A (en) | Map constructing method and system based on GPS, IMU and binocular vision | |
| US9251587B2 (en) | Motion estimation utilizing range detection-enhanced visual odometry | |
| Su et al. | GR-LOAM: LiDAR-based sensor fusion SLAM for ground robots on complex terrain | |
| CN108731672B (en) | Coal mining machine attitude detection system and method based on binocular vision and inertial navigation | |
| CN107909614B (en) | Positioning method of inspection robot in GPS failure environment | |
| CN108731670A (en) | Inertia/visual odometry combined navigation locating method based on measurement model optimization | |
| CN108475059A (en) | Autonomous vision guided navigation | |
| CN107966989A (en) | A kind of robot autonomous navigation system | |
| CN108235735A (en) | Positioning method and device, electronic equipment and computer program product | |
| CN112476433B (en) | Mobile robot positioning method based on identification array boundary | |
| CN207965645U (en) | A kind of robot autonomous navigation system | |
| KR102396675B1 (en) | Position estimation and 3d tunnel mapping system of underground mine autonomous robot using lidar sensor, and its method | |
| CN108413965A (en) | A kind of indoor and outdoor crusing robot integrated system and crusing robot air navigation aid | |
| Zheng et al. | An optimization-based UWB-IMU fusion framework for UGV | |
| CN108868772A (en) | A kind of continuous milling machine quickly collimates control method | |
| Adam et al. | Fusion of fixation and odometry for vehicle navigation | |
| CN106225779A (en) | Development machine alignment systems based on three laser labelling dot image and localization method | |
| Csaba et al. | Differences between Kinect and structured lighting sensor in robot navigation | |
| CN114964227A (en) | Coal mining machine combined navigation positioning system and method based on depth camera positioning correction | |
| Si et al. | A novel positioning method of anti-punching drilling robot based on the fusion of multi-IMUs and visual image | |
| Deusch et al. | Improving localization in digital maps with grid maps | |
| CN109839109A (en) | The absolute position and posture detection method of development machine based on image recognition and Multi-sensor Fusion |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |