CN116540763B - Intelligent monitoring management method and system for flight attitude of unmanned aerial vehicle - Google Patents
Intelligent monitoring management method and system for flight attitude of unmanned aerial vehicle Download PDFInfo
- Publication number
- CN116540763B CN116540763B CN202310808667.3A CN202310808667A CN116540763B CN 116540763 B CN116540763 B CN 116540763B CN 202310808667 A CN202310808667 A CN 202310808667A CN 116540763 B CN116540763 B CN 116540763B
- Authority
- CN
- China
- Prior art keywords
- node
- gesture
- search
- steady
- aerial vehicle
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 80
- 238000007726 management method Methods 0.000 title claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 126
- 238000004458 analytical method Methods 0.000 claims abstract description 65
- 230000005484 gravity Effects 0.000 claims abstract description 63
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 230000008859 change Effects 0.000 claims description 68
- 238000000034 method Methods 0.000 claims description 65
- 239000013598 vector Substances 0.000 claims description 65
- 238000000354 decomposition reaction Methods 0.000 claims description 40
- 230000009466 transformation Effects 0.000 claims description 34
- 238000003066 decision tree Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000001131 transforming effect Effects 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract description 10
- 238000004422 calculation algorithm Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 33
- 230000000694 effects Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 206010034719 Personality change Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention provides an intelligent monitoring management method and system for unmanned aerial vehicle flight attitude, which relate to the technical field of intelligent monitoring and comprise the following steps: obtaining a preset planning path based on the first unmanned aerial vehicle, performing depth-first search to obtain a search node set, performing primary identification, performing real-time gesture sensing to obtain a gesture monitoring data set, inputting the gesture monitoring data set into a gesture analysis module to obtain a first gesture rotation matrix, performing gravity component fusion, generating a second gesture rotation matrix, performing steady-state analysis on each node to output a steady-state index set, corresponding to the search node set, and performing monitoring reminding on the search node set according to the steady-state index set. The invention solves the technical problems that the traditional unmanned aerial vehicle flight attitude monitoring and management method only depends on a preset flight path and a simple control algorithm, and is difficult to respond to complex environmental factors such as various climates, terrains and the like in real time, so that the unmanned aerial vehicle has poor flight safety and stability.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring, in particular to an intelligent monitoring management method and system for unmanned aerial vehicle flight gestures.
Background
Along with the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicle has been widely used in a plurality of fields, such as agriculture, survey and drawing, take photo by plane, commodity circulation etc. in unmanned aerial vehicle flight process, the stability of flight gesture is crucial to guarantee flight safety and realization task target, however, the monitoring management method of unmanned aerial vehicle flight gesture that is commonly used still has certain drawback today, still has certain liftable space to unmanned aerial vehicle flight gesture's monitoring management.
Disclosure of Invention
The embodiment of the application provides an intelligent monitoring management method and system for the flight attitude of an unmanned aerial vehicle, which are used for solving the technical problems that the traditional unmanned aerial vehicle flight attitude monitoring and management method only depends on a preset flight path and a simple control algorithm, is difficult to respond to complex environmental factors such as various climates, terrains and the like in real time, and ensures that the flight safety and stability of the unmanned aerial vehicle are poor.
In view of the above problems, the embodiment of the application provides an intelligent monitoring and management method and system for unmanned aerial vehicle flight attitude.
In a first aspect, an embodiment of the present application provides an intelligent monitoring and managing method for a flight attitude of an unmanned aerial vehicle, where the method includes: according to the terminal of the ground station control system, a preset planning path based on the first unmanned aerial vehicle is obtained; performing depth-first search according to the path change characteristics of the preset planning path to obtain a search node set, and performing primary identification on the search node set; performing real-time gesture sensing on the first unmanned aerial vehicle according to a gesture sensing integrated device to obtain gesture monitoring data sets respectively corresponding to the search node sets; inputting the gesture monitoring data set into a gesture analysis module to obtain a first gesture rotation matrix; generating a second gesture rotation matrix by carrying out gravity component fusion on the first gesture rotation matrix; performing steady-state analysis on each node in the search node set according to the second gesture rotation matrix, and outputting a steady-state index set, wherein the steady-state index set is used for identifying dynamic stability indexes when each node performs gesture adjustment, and the steady-state index set corresponds to the search node set one by one; and monitoring and reminding the searching node set according to the steady state index set.
In a second aspect, an embodiment of the present application provides an intelligent monitoring management system for a flight attitude of an unmanned aerial vehicle, where the system includes: the system comprises a planned path acquisition module, a first unmanned aerial vehicle-based planning module and a second unmanned aerial vehicle-based planning module, wherein the planned path acquisition module is used for acquiring a preset planned path based on the first unmanned aerial vehicle according to a terminal of a ground station control system; the depth-first search module is used for carrying out depth-first search according to the path change characteristics of the preset planning path to obtain a search node set, and carrying out primary identification on the search node set; the real-time gesture sensing module is used for conducting real-time gesture sensing on the first unmanned aerial vehicle according to the gesture sensing integrated device to obtain gesture monitoring data sets respectively corresponding to the search node sets; the first matrix acquisition module is used for inputting the gesture monitoring data set into the gesture analysis module to obtain a first gesture rotation matrix; the second matrix acquisition module is used for generating a second gesture rotation matrix by carrying out gravity component fusion on the first gesture rotation matrix; the steady state analysis module is used for carrying out steady state analysis on each node in the searching node set according to the second gesture rotation matrix and outputting a steady state index set, wherein the steady state index set is used for identifying dynamic stability indexes when each node carries out gesture adjustment, and the steady state index set corresponds to the searching node set one by one; and the monitoring reminding module is used for monitoring and reminding the searching node set according to the steady-state index set.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
obtaining a preset planning path based on a first unmanned aerial vehicle, performing depth-first search to obtain a search node set, performing primary identification, performing real-time gesture sensing to obtain a gesture monitoring data set, inputting a first gesture rotation matrix obtained in a gesture analysis module, performing gravity component fusion to generate a second gesture rotation matrix, performing steady-state analysis on each node in the search node set, outputting a steady-state index set, wherein the steady-state index set corresponds to the search node set one by one, and monitoring and reminding the search node set according to the steady-state index set. The method solves the technical problems that the traditional unmanned aerial vehicle flight attitude monitoring and management method only depends on a preset flight path and a simple control algorithm, is difficult to respond to complex environmental factors such as various climates and terrains in real time, so that the unmanned aerial vehicle has poor flight safety and stability, realizes depth-first search and real-time attitude sensing of the preset planning path, fuses a gravity component and a steady-state analysis model, comprehensively considers the influence of the environmental factors on the flight attitude, realizes accurate attitude adjustment, and achieves the technical effects of improving the flight safety and stability.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
Fig. 1 is a schematic flow chart of an intelligent monitoring and managing method for unmanned aerial vehicle flight attitude according to an embodiment of the application;
fig. 2 is a schematic diagram of a flow chart of monitoring and reminding a search node set in an intelligent monitoring and managing method for unmanned aerial vehicle flight gestures according to an embodiment of the application;
fig. 3 is a schematic flow chart of generating a second gesture rotation matrix in the intelligent monitoring and managing method of the flight gesture of the unmanned aerial vehicle according to the embodiment of the application;
fig. 4 is a schematic structural diagram of an intelligent monitoring management system for unmanned aerial vehicle flight attitude according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a planned path acquisition module 10, a depth-first search module 20, a real-time attitude sensing module 30, a first matrix acquisition module 40, a second matrix acquisition module 50, a steady-state analysis module 60 and a monitoring reminding module 70.
Detailed Description
The embodiment of the application solves the technical problems that the traditional unmanned aerial vehicle flight attitude monitoring and management method only depends on a preset flight path and a simple control algorithm, and is difficult to respond to complex environmental factors such as various climates, terrains and the like in real time, so that the unmanned aerial vehicle flight safety and stability are poor, the depth-first search of the preset planning path and the real-time attitude sensing are realized, the gravity component and the steady-state analysis model are fused, the influence of the environmental factors on the flight attitude is comprehensively considered, the accurate attitude adjustment is realized, and the technical effects of improving the flight safety and stability are achieved.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent monitoring and managing method for a flight attitude of an unmanned aerial vehicle, where the method includes:
step S100: according to the terminal of the ground station control system, a preset planning path based on the first unmanned aerial vehicle is obtained;
Specifically, the ground station control system establishes communication connection with the unmanned aerial vehicle through radio signals, wi-Fi or other wireless communication technologies, so that the ground station control system can send instructions and receive data from the unmanned aerial vehicle, and the ground station control system receives basic information of the unmanned aerial vehicle, such as current position, speed, altitude, heading and the like, and the information is used for planning a preset path.
And setting target positions and other task related parameters of the unmanned aerial vehicle, integrating constraint conditions such as flight altitude, speed limit and no-fly zone, running a path planning algorithm, integrating factors such as the current position, the target positions and the constraint conditions of the unmanned aerial vehicle, and generating a preset planning path meeting the requirements. After confirming the preset planned path, sending the path data to the unmanned aerial vehicle through communication connection, and after receiving the path data, the unmanned aerial vehicle flies according to the preset planned path.
Through the steps, the ground station control system can effectively generate a preset planning path for the unmanned aerial vehicle and ensure that the unmanned aerial vehicle flies according to the expected path.
Step S200: performing depth-first search according to the path change characteristics of the preset planning path to obtain a search node set, and performing primary identification on the search node set;
Specifically, according to a preset planned path, key points and path change characteristics on the path are analyzed, wherein the key points are turning points, speed change points, height change points and the like on the path, and the path change characteristics are turning radius, climbing or descending angle and the like. Based on a preset planning path, a decision search tree is constructed, each node of the search decision tree represents a key point on the path, edges between the nodes represent connection between the key points, a root node of the search decision tree represents a starting position of the unmanned aerial vehicle, and leaf nodes represent target positions.
The depth-first search is performed from the root node of the search decision tree, and is a graph search algorithm, and the depth-first search is performed along the depth direction of the search decision tree until leaf nodes are reached or stop conditions are met. After the depth-first search is completed, all the nodes accessed in the search process are collected to form a search node set, and the set represents key points which possibly need to be subjected to gesture adjustment on a preset planning path.
In order to facilitate subsequent processing and analysis, unique identification is performed on each node in the search node set by using modes such as integers, character strings and the like, and the identification information comprises a hierarchy of the nodes in a search decision tree, an access sequence of the nodes in a search process and the like.
Further, the step S200 of the present application further includes:
step S210: analyzing the path change characteristics of the preset planning path to obtain path space angle change characteristics and path space vector change characteristics;
step S220: taking the path space angle change feature and the path space vector change feature as a first-level feature and a second-level feature respectively, and building a search decision tree;
step S230: acquiring a path change node set in the preset planning path;
step S240: and inputting the path change node set into the search decision tree to perform depth-first search to obtain the search node set.
Specifically, adjacent points on a preset planning path are analyzed, the spatial angle change between each pair of adjacent points is calculated, the spatial angle changes are counted, and path spatial angle change characteristics are obtained and used for describing the angle change condition of the unmanned aerial vehicle along the preset planning path in the flight process; by the same method, path space vector change characteristics are obtained, and the characteristics are used for describing displacement change conditions of the unmanned aerial vehicle along a preset planning path in the flight process.
And creating a root node of the decision tree according to a starting point of a preset planning path, wherein the root node represents an initial state of the unmanned aerial vehicle and comprises position and posture information of the unmanned aerial vehicle. According to the space angle change characteristics of the path, adding first-level characteristic nodes, namely adding child nodes for each root node, representing the angle change state of the unmanned aerial vehicle in the flight process, wherein each child node contains angle change information with a father node; according to the path space vector change characteristics, adding secondary characteristic nodes, namely adding sub-nodes for each primary characteristic node, and representing the displacement change state of the unmanned aerial vehicle in the flight process. This step is repeated until the end of the preset planned path is reached.
And checking each point on the path one by one along the preset planning path from the starting point to the end point, calculating the angle change and the vector change between each point and the previous point and the next point, and adding the point into the path change node set if the change values exceed the preset threshold value, which indicates that the gesture of the unmanned aerial vehicle is obviously changed at the point.
Further, step S240 of the present application further includes:
step S241: acquiring node quantity characteristics of the path change node set;
Step S242: configuring a preset optimizing interval, optimizing from the preset optimizing interval according to the node quantity characteristics to obtain a first optimizing result, wherein obtaining the first optimizing result comprises setting the quantity of initialized nodes, calculating the neighborhood optimizing result of the preset optimizing interval based on the quantity of initialized nodes to obtain an optimal result, and obtaining the searching node set.
Specifically, traversing the path change node set, counting the number of nodes in the path change node set, and analyzing the node number characteristics of the path change node set, wherein the characteristics are used for evaluating the complexity degree of the attitude change of the unmanned aerial vehicle in the flight process.
According to the node number characteristics of the path change node set, a preset optimizing interval, for example, a range between the minimum value and the maximum value of the node number is set for the optimizing process. Selecting an initial node number in a preset optimizing interval as a starting point of optimizing, and carrying out neighborhood optimizing in the preset optimizing interval based on the selected initial node number, wherein the neighborhood optimizing is a local searching method which is used for optimizing a problem by searching a better solution in the neighborhood of a current solution, and specifically, a heuristic method such as simulated annealing is used for searching the optimal solution in the neighborhood. Recording an optimal solution in the neighborhood optimizing process until the neighborhood optimizing converges or reaches preset iteration times, taking the found optimal solution as a first optimizing result, and updating a searching node set according to the first optimizing result, wherein the searching node set comprises adding or deleting searching nodes so as to better match the flight attitude change corresponding to the optimal solution.
Further, after step S242, the method further includes:
step S243: carrying out neighborhood index analysis on two adjacent search node sets in the search node sets to obtain N neighborhood approximate indexes;
step S244: based on the N neighborhood approximate indexes, identifying abnormal search nodes which are larger than a preset approximate index in the N neighborhood approximate indexes, and eliminating the abnormal search nodes from the search node set.
Specifically, a pair of adjacent search nodes is selected from the search node set, and a neighborhood index between the adjacent search nodes is calculated, wherein the neighborhood index is used for measuring the difference degree between the two adjacent search nodes, such as posture change, speed change and the like. Traversing the whole search node set, analyzing all adjacent search node pairs, recording the neighborhood indexes obtained by calculation between each pair of adjacent search nodes to obtain a neighborhood approximate index set, wherein N is equal to the number of the adjacent search node pairs in the search node set, for example, 30 nodes in the search node set, and the number N of the adjacent search node pairs is 15.
And determining a preset approximate index threshold according to the flight characteristics and the actual application scene of the unmanned aerial vehicle, wherein the threshold is used for judging whether the neighborhood approximate index exceeds a normal range, so as to determine whether an abnormal search node exists. Traversing the neighborhood approximate index set, comparing each neighborhood approximate index with a preset approximate index threshold, if a certain neighborhood approximate index is larger than the preset approximate index threshold, indicating that a larger difference exists between corresponding search node pairs, namely an abnormal search node, and removing the abnormal search node from the search node set, so that only nodes with the difference degree in a normal range between adjacent search nodes are reserved in the search node set.
Step S300: performing real-time gesture sensing on the first unmanned aerial vehicle according to a gesture sensing integrated device to obtain gesture monitoring data sets respectively corresponding to the search node sets;
specifically, an attitude sensing integrated device is installed on the unmanned aerial vehicle, and the device is an integration of various sensors, and comprises a gyroscope, an accelerometer, a magnetometer and other sensors, and is used for measuring attitude information of the unmanned aerial vehicle in real time, such as a rolling angle, a pitch angle and a yaw angle, and the attitude sensing integrated device is used for measuring the attitude of the unmanned aerial vehicle in real time to acquire attitude data. Matching the gesture data with a search node set in a preset planning path, and recording the current gesture information of the unmanned aerial vehicle when the unmanned aerial vehicle reaches the search node, wherein the information is used for subsequent gesture analysis and adjustment.
And integrating the gesture information of the unmanned aerial vehicle on the search nodes to form a gesture monitoring data set, wherein the data set corresponds to the search node set one by one and contains the real-time gesture information of the unmanned aerial vehicle on each search node.
Step S400: inputting the gesture monitoring data set into a gesture analysis module to obtain a first gesture rotation matrix;
Specifically, the gesture analysis module is used for processing and analyzing gesture monitoring data of the unmanned aerial vehicle, the gesture analysis module calculates a rotation matrix of the unmanned aerial vehicle on each search node according to the input gesture monitoring data, the rotation matrix is a 3*3 matrix, the rotation change from a local coordinate system to a global coordinate system of the unmanned aerial vehicle is represented, the obtained rotation machines are integrated, a first gesture rotation matrix is obtained, and the rotation information of the unmanned aerial vehicle on each search node is contained in the matrix for subsequent gesture analysis and adjustment.
Step S500: generating a second gesture rotation matrix by carrying out gravity component fusion on the first gesture rotation matrix;
further, as shown in fig. 3, step S500 of the present application further includes:
step S510: carrying out vector recognition on the first gesture rotation matrix to obtain a first decomposition matrix, wherein the first decomposition matrix is a matrix formed by all vectors in the gesture rotation matrix, and the vectors comprise related vectors of vertical stress;
specifically, the first gesture rotation matrix is analyzed to identify a vector containing a vertical force component, wherein the vertical force component refers to a force opposite to the direction of gravitational attraction, i.e. a force perpendicular to the surface of the earth during the flight of the unmanned aerial vehicle. And extracting related vectors containing vertical stress components from the first attitude rotation matrix, wherein the related vectors represent the influence of gravity components of the unmanned aerial vehicle in the flight process, and combining the extracted related vectors into a new matrix called a first decomposition matrix, wherein the matrix contains attitude information of the unmanned aerial vehicle related to the vertical stress in the flight process.
Step S520: obtaining a second decomposition matrix by carrying out gravity characteristic transformation on the first decomposition matrix;
further, step S520 of the present application further includes:
step S521: acquiring a gravity sensing dataset of the first unmanned aerial vehicle;
step S522: carrying out gravity analysis on each vector in the first decomposition matrix based on the gravity sensing data set to obtain a vector for identifying isotropic vertical stress and a vector for identifying reverse vertical stress;
step S523: generating an equidirectional transformation coefficient and a reverse transformation coefficient according to the vector of the equidirectional vertical stress of the mark and the vector of the reverse vertical stress of the mark;
step S524: and carrying out gravity characteristic transformation on the first decomposition matrix by using the equidirectional transformation coefficient and the inverse transformation coefficient to obtain a second decomposition matrix.
Specifically, a gravity sensor, such as a gyroscope and the like, capable of detecting gravity change is arranged on the unmanned aerial vehicle, and in the flight process of the unmanned aerial vehicle, the gravity sensor measures gravity component data received by the unmanned aerial vehicle in real time in the flight process, and the gravity component data comprises information such as gravity acceleration, gravity angle and the like in all directions.
Carrying out gravity analysis on all relevant vectors in the first decomposition matrix by utilizing a gravity sensing data set, namely calculating gravity components of each vector in the first decomposition matrix in all directions through dot products of the vectors and gravity acceleration data, wherein the vector of the sign equidirectional vertical stress is the vector with the same gravity direction, and the vector represents the forward gravity influence of the unmanned aerial vehicle in the flight process; the vectors for identifying the reverse vertical stress are vectors opposite to the gravity direction, and the vectors represent the reverse gravity influence of the unmanned aerial vehicle in the flight process.
For each vector of the equal vertical stress of the mark, calculating the ratio of the component which is the same as the gravity direction to the gravity acceleration, and averaging the ratios to obtain an equal transformation coefficient, wherein the equal transformation coefficient represents the influence degree of the forward gravity influence on the gesture stability of the unmanned aerial vehicle in the flight process. And calculating the inverse transformation coefficient by the same method, wherein the inverse transformation coefficient represents the influence degree of the inverse gravity on the attitude stability of the unmanned aerial vehicle in the flight process.
Scaling the identification isotropic vertical stress vector in the first decomposition matrix by using the isotropic transformation coefficient, wherein the scaled vector can more accurately reflect the forward gravity influence of the unmanned aerial vehicle in the flight process; scaling the identified reverse vertical stress vector in the first decomposition matrix by using the reverse transformation coefficient, wherein the scaled vector can more accurately reflect the reverse gravity influence of the unmanned aerial vehicle in the flight process. And recombining the vector scaled by the isotropic transformation coefficient and the inverse transformation coefficient to generate a new decomposition matrix, namely a second decomposition matrix, wherein the second decomposition matrix can better reflect the actual gravity influence of the unmanned aerial vehicle in the flight process, thereby providing more accurate information for the subsequent gesture stability analysis.
Step S530: and restoring the first gesture rotation matrix according to the second decomposition matrix to generate a second gesture rotation matrix corresponding to each node in the search node set.
Specifically, the vertical stress related vector subjected to gravity characteristic transformation in the second decomposition matrix is combined with other vectors which are not subjected to gravity characteristic transformation in the first gesture rotation matrix, so that a matrix containing all gesture vectors subjected to gravity component fusion is obtained, the first gesture rotation matrix is restored through the combined vector matrix, the operations such as inverse transformation of the matrix and matrix multiplication are included, and the restored gesture rotation matrix can describe the gravity influence of the unmanned aerial vehicle in the flight process more accurately. And generating a corresponding second gesture rotation matrix for each node according to the position information of each node in the search node set, wherein the second gesture rotation matrix comprises gesture information subjected to gravity component fusion and is used for subsequent steady-state analysis and gesture adjustment.
Step S600: performing steady-state analysis on each node in the search node set according to the second gesture rotation matrix, and outputting a steady-state index set, wherein the steady-state index set is used for identifying dynamic stability indexes when each node performs gesture adjustment, and the steady-state index set corresponds to the search node set one by one;
Specifically, a steady-state analysis model is established and used for evaluating the dynamic stability of the unmanned aerial vehicle on each search node, the model integrates the information of the dynamic characteristics, the environmental factors, the second gesture rotation matrix and the like of the unmanned aerial vehicle, and the second gesture rotation matrix is input into the steady-state analysis model. And carrying out steady-state analysis on each node in the search node set according to the steady-state analysis model, and calculating a dynamic stability index of each node during unmanned aerial vehicle posture adjustment, wherein the stability index is a real value, the stability of the unmanned aerial vehicle on the node is represented, and the larger the value is, the better the stability is represented. And integrating the dynamic stability indexes on each search node to form a steady state index set, wherein the steady state index set corresponds to the search node set one by one and is used for representing the dynamic stability of the unmanned aerial vehicle when the gesture of each node is adjusted.
Step S700: and monitoring and reminding the searching node set according to the steady state index set.
Specifically, the steady state index set is analyzed to find out abnormal values or steady state indexes lower than a preset threshold value, wherein the steady state indexes represent poor dynamic stability of the unmanned aerial vehicle on the corresponding search node, and measures are needed to be taken for posture adjustment. And generating responsive detection reminding information for the analyzed abnormal or low-stability nodes, wherein the detection reminding information comprises detailed information such as node positions, dynamic stability indexes, possible reasons and the like, and the reasons comprise environmental factors such as wind speed, air pressure and the like. And sending the generated detection reminding information to a ground station control system, and after the ground station control system receives the reminding information, carrying out real-time posture adjustment on the unmanned aerial vehicle according to the reminding content, such as modifying the flight altitude, changing the heading and the like, so that the safety and the stability of the unmanned aerial vehicle in the flight process are improved.
Further, as shown in fig. 2, step S700 of the present application further includes:
step S710: when the first unmanned aerial vehicle flies to a node with a primary identifier according to the preset planning path, monitoring a continuous steady-state index, wherein the continuous steady-state index is used for identifying a steady index for dynamically adjusting the gesture of the first unmanned aerial vehicle when the first unmanned aerial vehicle flies to the node with the primary identifier;
step S720: carrying out stability analysis on the continuous steady-state index and outputting index stability;
step S730: and if the index stability is greater than a preset stability index, generating first reminding information, and reminding the first unmanned aerial vehicle to allow to enter a posture compensation state according to the first reminding information.
Specifically, during the flight of the unmanned aerial vehicle, the position of the unmanned aerial vehicle is concerned in real time, and when the unmanned aerial vehicle flies to a node with a primary mark in a preset planning path, the continuous steady state index monitoring is triggered. And acquiring a continuous steady-state index corresponding to the primary identification node, which is the current flying arrival, according to the steady-state index set, wherein the index represents the stability of the unmanned aerial vehicle when the current node is subjected to gesture adjustment.
And (3) carrying out stability analysis on continuous steady-state index data by using a statistical method, namely determining whether the statistical characteristics of the mean value, the variance and the like of the data on a time sequence are kept unchanged along with time, and determining the stability condition of attitude adjustment of the unmanned aerial vehicle in the flight process. And outputting index stability according to the result of the stability analysis, wherein the index stability is used for indicating the overall stability of the unmanned aerial vehicle in the attitude adjustment in the flight process, and if the index stability is higher, the stability of the unmanned aerial vehicle in the attitude adjustment in the flight process is better.
According to the safety and stability requirements of unmanned aerial vehicle flight attitude adjustment, a preset stability index is set, the index is used for being compared with the index stability obtained through actual calculation, so that the stability condition of the unmanned aerial vehicle during attitude adjustment in the flight process is judged, if the index stability is greater than the preset stability index, the integral stability of the unmanned aerial vehicle during attitude adjustment in the flight process is good, the unmanned aerial vehicle can be allowed to enter an attitude compensation state, at the moment, first reminding information is generated, and the reminding information comprises the current position of the unmanned aerial vehicle, an index stability value, a prompt for suggesting to enter the attitude compensation state and the like.
Further, step S710 of the present application further includes:
step S711: node time sequence period identification is carried out on the searching node set, and time sequence distribution information is obtained;
step S712: determining a node preset period according to the time sequence distribution information, wherein the node preset period is a period for monitoring steady state indexes of each node in the searching node set;
step S713: and monitoring the continuous steady-state index according to the node preset period.
Specifically, in the flight process of the unmanned aerial vehicle, a search node set is obtained according to a preset planning path, information such as the position and the time stamp of each search node is obtained, a time sequence analysis method is used for carrying out node time sequence period identification on the search node set, and a periodic rule of the search node in time is obtained, for example, the unmanned aerial vehicle has a high gesture adjustment requirement in a specific time period. And acquiring time sequence distribution information of the search node according to the period identification result, wherein the time sequence distribution information is used for describing distribution characteristics of the search node in the time dimension, such as a periodic high-frequency posture adjustment interval, a low-frequency posture adjustment interval and the like.
According to the time sequence distribution information obtained through analysis, a preset period for monitoring steady state indexes of each node in the searching node set is determined, the preset period of each node is used for indicating a time interval with higher or lower gesture adjustment requirements in the flight process of the unmanned aerial vehicle, for example, if the gesture adjustment requirements are found to be higher in a certain time period, the time period can be used as the preset period of each node.
The determined node preset period is applied to the intelligent monitoring management process of the unmanned aerial vehicle flight attitude, the monitoring and reminding of unmanned aerial vehicle attitude adjustment are enhanced in the corresponding time interval, so that the stability and safety of the unmanned aerial vehicle in the flight process are ensured, and meanwhile, the frequency of monitoring and reminding is reduced in the time interval with lower attitude adjustment requirements, so that the working efficiency of the system is improved. The time points, which are required to continuously monitor the continuous steady-state index in the unmanned aerial vehicle flight process, are set, and comprise time intervals with high requirements for posture adjustment and time points of other key nodes. And monitoring the continuous steady state index of the unmanned aerial vehicle in real time at a set monitoring time point.
In summary, the intelligent monitoring and management method and system for the unmanned aerial vehicle flight attitude provided by the embodiment of the application have the following technical effects:
Obtaining a preset planning path based on a first unmanned aerial vehicle, performing depth-first search to obtain a search node set, performing primary identification, performing real-time gesture sensing to obtain a gesture monitoring data set, inputting a first gesture rotation matrix obtained in a gesture analysis module, performing gravity component fusion to generate a second gesture rotation matrix, performing steady-state analysis on each node in the search node set, outputting a steady-state index set, wherein the steady-state index set corresponds to the search node set one by one, and monitoring and reminding the search node set according to the steady-state index set. The method solves the technical problems that the traditional unmanned aerial vehicle flight attitude monitoring and management method only depends on a preset flight path and a simple control algorithm, is difficult to respond to complex environmental factors such as various climates and terrains in real time, so that the unmanned aerial vehicle has poor flight safety and stability, realizes depth-first search and real-time attitude sensing of the preset planning path, fuses a gravity component and a steady-state analysis model, comprehensively considers the influence of the environmental factors on the flight attitude, realizes accurate attitude adjustment, and achieves the technical effects of improving the flight safety and stability.
Example two
Based on the same inventive concept as the intelligent monitoring and managing method for the flight attitude of the unmanned aerial vehicle in the foregoing embodiment, as shown in fig. 4, the present application provides an intelligent monitoring and managing system for the flight attitude of the unmanned aerial vehicle, where the system includes:
the planned path acquisition module 10 is used for acquiring a preset planned path based on the first unmanned aerial vehicle according to the terminal of the ground station control system;
the depth-first search module 20 is configured to perform depth-first search according to the path change feature of the preset planned path, obtain a search node set, and identify the search node set once;
the real-time gesture sensing module 30 is configured to perform real-time gesture sensing on the first unmanned aerial vehicle according to a gesture sensing integrated device, so as to obtain gesture monitoring data sets respectively corresponding to the search node sets;
the first matrix acquisition module 40 is configured to input the gesture monitoring dataset into the gesture analysis module to obtain a first gesture rotation matrix;
the second matrix acquisition module 50 is configured to generate a second gesture rotation matrix by performing gravity component fusion on the first gesture rotation matrix by the second matrix acquisition module 50;
The steady state analysis module 60 is configured to perform steady state analysis on each node in the search node set according to the second gesture rotation matrix, and output a steady state index set, where the steady state index set is used to identify a dynamic stability index when each node performs gesture adjustment, and the steady state index set corresponds to the search node set one to one;
the monitoring reminding module 70 is configured to monitor and remind the search node set according to the steady state index set by the monitoring reminding module 70.
Further, the system further comprises:
the continuous steady state index monitoring module is used for monitoring a continuous steady state index when the first unmanned aerial vehicle flies to a node with a primary identifier according to the preset planning path, wherein the continuous steady state index is used for identifying a steady index for dynamically adjusting the gesture of the first unmanned aerial vehicle when the first unmanned aerial vehicle flies to the node with the primary identifier;
the stability analysis module is used for carrying out stability analysis on the continuous steady-state indexes and outputting index stability;
and the first reminding information generation module is used for generating first reminding information if the index stability is greater than a preset stability index, and reminding the first unmanned aerial vehicle to allow the first unmanned aerial vehicle to enter a posture compensation state according to the first reminding information.
Further, the system further comprises:
the period identification module is used for carrying out node time sequence period identification on the search node set and acquiring time sequence distribution information;
the preset period determining module is used for determining a node preset period according to the time sequence distribution information, wherein the node preset period is a period of monitoring steady state indexes by each node in the searching node set;
and the steady-state index monitoring module is used for monitoring the continuous steady-state index according to the node preset period.
Further, the system further comprises:
the vector recognition module is used for carrying out vector recognition on the first gesture rotation matrix to obtain a first decomposition matrix, wherein the first decomposition matrix is a matrix formed by related vectors containing vertical stress in all vectors in the gesture rotation matrix;
the gravity characteristic transformation module is used for obtaining a second decomposition matrix by carrying out gravity characteristic transformation on the first decomposition matrix;
and the restoring module is used for restoring the first gesture rotation matrix according to the second decomposition matrix to generate a second gesture rotation matrix corresponding to each node in the searching node set.
Further, the system further comprises:
the gravity sensing data acquisition module is used for acquiring a gravity sensing data set of the first unmanned aerial vehicle;
the gravity analysis module is used for carrying out gravity analysis on each vector in the first decomposition matrix based on the gravity sensing data set to obtain a vector for identifying isotropic vertical stress and a vector for identifying reverse vertical stress;
the transformation coefficient generation module is used for generating an equidirectional transformation coefficient and a reverse transformation coefficient according to the vector of the identification equidirectional vertical stress and the vector of the identification reverse vertical stress;
and the gravity characteristic transformation module is used for carrying out gravity characteristic transformation on the first decomposition matrix by using the equidirectional transformation coefficient and the inverse transformation coefficient to obtain a second decomposition matrix.
Further, the system further comprises:
the path change feature analysis module is used for analyzing the path change feature of the preset planning path to obtain a path space angle change feature and a path space vector change feature;
the search decision tree building module is used for building a search decision tree by taking the path space angle change feature and the path space vector change feature as a primary feature and a secondary feature respectively;
The path change node acquisition module is used for acquiring a path change node set in the preset planning path;
and the depth-first searching module is used for inputting the path change node set into the searching decision tree to perform depth-first searching to obtain the searching node set.
Further, the system further comprises:
the node quantity feature acquisition module is used for acquiring the node quantity feature of the path change node set;
the optimizing module is used for configuring a preset optimizing interval, optimizing the preset optimizing interval according to the node quantity characteristics to obtain a first optimizing result, wherein the obtaining of the first optimizing result comprises the steps of setting the quantity of initialized nodes, calculating the neighborhood optimizing result of the preset optimizing interval based on the quantity of the initialized nodes to obtain an optimal result, and obtaining the searching node set.
Further, the system further comprises:
the neighborhood index analysis module is used for carrying out neighborhood index analysis on two adjacent search node sets in the search node sets to obtain N neighborhood approximate indexes;
the abnormal search node identification module is used for identifying abnormal search nodes larger than a preset approximate index in the N neighborhood approximate indexes based on the N neighborhood approximate indexes, and eliminating the abnormal search nodes from the search node set.
Through the foregoing detailed description of the method for intelligently monitoring and managing the flight attitude of the unmanned aerial vehicle, those skilled in the art can clearly know the method and the system for intelligently monitoring and managing the flight attitude of the unmanned aerial vehicle in the embodiment, and for the device disclosed in the embodiment, the description is relatively simple because the device corresponds to the method disclosed in the embodiment, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. An intelligent monitoring and management method for unmanned aerial vehicle flight attitude is characterized by comprising the following steps:
according to the terminal of the ground station control system, a preset planning path based on the first unmanned aerial vehicle is obtained;
Performing depth-first search according to the path change characteristics of the preset planning path to obtain a search node set, and performing primary identification on the search node set;
performing real-time gesture sensing on the first unmanned aerial vehicle according to a gesture sensing integrated device to obtain gesture monitoring data sets respectively corresponding to the search node sets;
inputting the gesture monitoring data set into a gesture analysis module to obtain a first gesture rotation matrix;
generating a second gesture rotation matrix by carrying out gravity component fusion on the first gesture rotation matrix;
performing steady-state analysis on each node in the search node set according to the second gesture rotation matrix, and outputting a steady-state index set, wherein the steady-state index set is used for identifying dynamic stability indexes when each node performs gesture adjustment, and the steady-state index set corresponds to the search node set one by one, and performing steady-state analysis on each node in the search node set according to the second gesture rotation matrix, and outputting a steady-state index set comprises: establishing a steady-state analysis model, inputting the second gesture rotation matrix into the steady-state analysis model, carrying out steady-state analysis on each node in the search node set according to the steady-state analysis model, calculating a dynamic stability index of each node unmanned aerial vehicle during gesture adjustment, and integrating the dynamic stability indexes on each search node to obtain a steady-state index set;
Monitoring and reminding the searching node set according to the steady state index set;
the depth-first search is performed according to the path change characteristics of the preset planning path, and the method comprises the following steps:
analyzing the path change characteristics of the preset planning path to obtain path space angle change characteristics and path space vector change characteristics;
taking the path space angle change feature and the path space vector change feature as a first-level feature and a second-level feature respectively, and building a search decision tree;
acquiring a path change node set in the preset planning path;
inputting the path change node set into the search decision tree to perform depth-first search to obtain the search node set;
generating a second attitude and rotation matrix by carrying out gravity component fusion on the first attitude and rotation matrix, wherein the method comprises the following steps:
carrying out vector recognition on the first gesture rotation matrix to obtain a first decomposition matrix, wherein the first decomposition matrix is a matrix formed by all vectors in the gesture rotation matrix, and the vectors comprise related vectors of vertical stress;
obtaining a second decomposition matrix by carrying out gravity characteristic transformation on the first decomposition matrix;
And restoring the first gesture rotation matrix according to the second decomposition matrix to generate a second gesture rotation matrix corresponding to each node in the search node set.
2. The method of claim 1, wherein the set of search nodes is monitored for reminders based on the set of steady state indices, the method comprising:
when the first unmanned aerial vehicle flies to a node with a primary identifier according to the preset planning path, monitoring a continuous steady-state index, wherein the continuous steady-state index is used for identifying a steady index for dynamically adjusting the gesture of the first unmanned aerial vehicle when the first unmanned aerial vehicle flies to the node with the primary identifier;
carrying out stability analysis on the continuous steady-state index and outputting index stability;
and if the index stability is greater than a preset stability index, generating first reminding information, and reminding the first unmanned aerial vehicle to allow to enter a posture compensation state according to the first reminding information.
3. The method of claim 2, wherein the method further comprises:
node time sequence period identification is carried out on the searching node set, and time sequence distribution information is obtained;
determining a node preset period according to the time sequence distribution information, wherein the node preset period is a period for monitoring steady state indexes of each node in the searching node set;
And monitoring the continuous steady-state index according to the node preset period.
4. The method of claim 1, wherein the second decomposition matrix is obtained by gravity eigen transforming the first decomposition matrix, the method further comprising:
acquiring a gravity sensing dataset of the first unmanned aerial vehicle;
carrying out gravity analysis on each vector in the first decomposition matrix based on the gravity sensing data set to obtain a vector for identifying isotropic vertical stress and a vector for identifying reverse vertical stress;
generating an equidirectional transformation coefficient and a reverse transformation coefficient according to the vector of the equidirectional vertical stress of the mark and the vector of the reverse vertical stress of the mark;
and carrying out gravity characteristic transformation on the first decomposition matrix by using the equidirectional transformation coefficient and the inverse transformation coefficient to obtain a second decomposition matrix.
5. The method of claim 1, wherein the method further comprises:
acquiring node quantity characteristics of the path change node set;
configuring a preset optimizing interval, optimizing from the preset optimizing interval according to the node quantity characteristics to obtain a first optimizing result, wherein obtaining the first optimizing result comprises setting the quantity of initialized nodes, calculating the neighborhood optimizing result of the preset optimizing interval based on the quantity of initialized nodes to obtain an optimal result, and obtaining the searching node set.
6. The method of claim 5, wherein after obtaining the set of search nodes, the method further comprises:
carrying out neighborhood index analysis on two adjacent search node sets in the search node sets to obtain N neighborhood approximate indexes;
based on the N neighborhood approximate indexes, identifying abnormal search nodes which are larger than a preset approximate index in the N neighborhood approximate indexes, and eliminating the abnormal search nodes from the search node set.
7. An intelligent monitoring management system for unmanned aerial vehicle flight attitude, which is characterized by comprising:
the system comprises a planned path acquisition module, a first unmanned aerial vehicle-based planning module and a second unmanned aerial vehicle-based planning module, wherein the planned path acquisition module is used for acquiring a preset planned path based on the first unmanned aerial vehicle according to a terminal of a ground station control system;
the depth-first search module is used for carrying out depth-first search according to the path change characteristics of the preset planning path to obtain a search node set, and carrying out primary identification on the search node set;
the real-time gesture sensing module is used for conducting real-time gesture sensing on the first unmanned aerial vehicle according to the gesture sensing integrated device to obtain gesture monitoring data sets respectively corresponding to the search node sets;
The first matrix acquisition module is used for inputting the gesture monitoring data set into the gesture analysis module to obtain a first gesture rotation matrix;
the second matrix acquisition module is used for generating a second gesture rotation matrix by carrying out gravity component fusion on the first gesture rotation matrix;
the steady state analysis module is used for carrying out steady state analysis on each node in the searching node set according to the second gesture rotation matrix and outputting a steady state index set, wherein the steady state index set is used for identifying dynamic stability indexes when each node carries out gesture adjustment, the steady state index set corresponds to the searching node set one by one, the steady state analysis is carried out on each node in the searching node set according to the second gesture rotation matrix and outputting the steady state index set, and the steady state analysis module comprises: establishing a steady-state analysis model, inputting the second gesture rotation matrix into the steady-state analysis model, performing steady-state analysis on each node in the search node set according to the steady-state analysis model, calculating a dynamic stability index of each node unmanned aerial vehicle during gesture adjustment, and integrating the dynamic stability indexes on each search node to obtain a steady-state index set;
The monitoring reminding module is used for monitoring and reminding the searching node set according to the steady-state index set;
the path change feature analysis module is used for analyzing the path change feature of the preset planning path to obtain a path space angle change feature and a path space vector change feature;
the search decision tree building module is used for building a search decision tree by taking the path space angle change feature and the path space vector change feature as a primary feature and a secondary feature respectively;
the path change node acquisition module is used for acquiring a path change node set in the preset planning path;
the depth-first searching module is used for inputting the path change node set into the searching decision tree to perform depth-first searching to obtain the searching node set;
the vector recognition module is used for carrying out vector recognition on the first gesture rotation matrix to obtain a first decomposition matrix, wherein the first decomposition matrix is a matrix formed by related vectors containing vertical stress in all vectors in the gesture rotation matrix;
the gravity characteristic transformation module is used for obtaining a second decomposition matrix by carrying out gravity characteristic transformation on the first decomposition matrix;
And the restoring module is used for restoring the first gesture rotation matrix according to the second decomposition matrix to generate a second gesture rotation matrix corresponding to each node in the searching node set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310808667.3A CN116540763B (en) | 2023-07-04 | 2023-07-04 | Intelligent monitoring management method and system for flight attitude of unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310808667.3A CN116540763B (en) | 2023-07-04 | 2023-07-04 | Intelligent monitoring management method and system for flight attitude of unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116540763A CN116540763A (en) | 2023-08-04 |
| CN116540763B true CN116540763B (en) | 2023-09-08 |
Family
ID=87458143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310808667.3A Active CN116540763B (en) | 2023-07-04 | 2023-07-04 | Intelligent monitoring management method and system for flight attitude of unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116540763B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001033271A (en) * | 1999-06-30 | 2001-02-09 | Gya Min-Chun | Flight route plan, topography-avoidance and status recognition system, for general purpose aircraft |
| CN106840143A (en) * | 2017-02-15 | 2017-06-13 | 南京信息工程大学 | A kind of method for differentiating underwater robot attitude stabilization |
| CN108871351A (en) * | 2018-08-02 | 2018-11-23 | 哈尔滨工程大学 | A kind of matched dynamic path planning method of AUV sea-floor relief |
| CN115016458A (en) * | 2022-05-05 | 2022-09-06 | 安徽理工大学 | Method for planning path of tunnel exploration robot based on RRT algorithm |
| CN115859461A (en) * | 2022-11-16 | 2023-03-28 | 中国人民解放军国防科技大学 | Longitudinal controllable domain and stability analysis method for low-speed fixed wing unmanned aerial vehicle |
-
2023
- 2023-07-04 CN CN202310808667.3A patent/CN116540763B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001033271A (en) * | 1999-06-30 | 2001-02-09 | Gya Min-Chun | Flight route plan, topography-avoidance and status recognition system, for general purpose aircraft |
| CN106840143A (en) * | 2017-02-15 | 2017-06-13 | 南京信息工程大学 | A kind of method for differentiating underwater robot attitude stabilization |
| CN108871351A (en) * | 2018-08-02 | 2018-11-23 | 哈尔滨工程大学 | A kind of matched dynamic path planning method of AUV sea-floor relief |
| CN115016458A (en) * | 2022-05-05 | 2022-09-06 | 安徽理工大学 | Method for planning path of tunnel exploration robot based on RRT algorithm |
| CN115859461A (en) * | 2022-11-16 | 2023-03-28 | 中国人民解放军国防科技大学 | Longitudinal controllable domain and stability analysis method for low-speed fixed wing unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116540763A (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106714110B (en) | Wi-Fi position fingerprint map automatic construction method and system | |
| CN114419152B (en) | Target detection and tracking method and system based on multi-dimensional point cloud characteristics | |
| Peng et al. | A unified framework for joint mobility prediction and object profiling of drones in UAV networks | |
| US9507053B2 (en) | Using aircraft trajectory data to infer atmospheric conditions | |
| CN108426582B (en) | Indoor three-dimensional map matching method for pedestrians | |
| EP4155679A2 (en) | Positioning method and apparatus based on lane line and feature point | |
| Jamil et al. | Enhanced Kalman filter algorithm using fuzzy inference for improving position estimation in indoor navigation | |
| Qiu et al. | Automatic extraction of road networks from GPS traces | |
| Wang et al. | Deep neural network‐based Wi‐Fi/pedestrian dead reckoning indoor positioning system using adaptive robust factor graph model | |
| CN116540763B (en) | Intelligent monitoring management method and system for flight attitude of unmanned aerial vehicle | |
| CN117095314B (en) | Target detection and re-identification method under cross-domain multi-dimensional air-space environment | |
| Zhao et al. | Factor graph based multi-source data fusion for wireless localization | |
| Sasaki et al. | Road segment interpolation for incomplete road data | |
| Dewan et al. | Som-tc: Self-organizing map for hierarchical trajectory clustering | |
| CN114674317A (en) | Self-correcting dead reckoning system and method based on activity recognition and fusion filtering | |
| CN114721377A (en) | Improved Cartogrier based SLAM indoor blind guiding robot control method | |
| US11113292B2 (en) | Feature data storage apparatus and driving feature and distribution databases | |
| Baccar et al. | Intelligent type 2 fuzzy-based mobile application for indoor geolocalization | |
| Zhang et al. | A Real Time Traffic Flow Model Based on Deep Learning. | |
| CN115662167B (en) | Automatic driving map construction method, automatic driving method and related devices | |
| Yao et al. | Robust Magnetic Field Loop Closure Detection for Low-Cost Robot’s Localization and Mapping | |
| Al-Assaad et al. | Statistical modelling of digital elevation models for GNSS-based navigation | |
| Xu et al. | Online map matching algorithm using segment angle based on hidden Markov model | |
| KR102619131B1 (en) | Satellite Data Estimation Method and System for Missing Value | |
| CN112866899B (en) | Man-machine cooperation oriented lunar communication and navigation integration realization method and device |
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 |