CN113093792A - Underground space detection system based on unmanned aerial vehicle - Google Patents
Underground space detection system based on unmanned aerial vehicle Download PDFInfo
- Publication number
- CN113093792A CN113093792A CN202110319716.8A CN202110319716A CN113093792A CN 113093792 A CN113093792 A CN 113093792A CN 202110319716 A CN202110319716 A CN 202110319716A CN 113093792 A CN113093792 A CN 113093792A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- underground space
- algorithm
- flight
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 230000000007 visual effect Effects 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 16
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 15
- 230000010365 information processing Effects 0.000 claims abstract description 8
- 238000013459 approach Methods 0.000 claims abstract description 6
- 230000003044 adaptive effect Effects 0.000 claims abstract description 4
- 238000013528 artificial neural network Methods 0.000 claims abstract description 4
- 239000002245 particle Substances 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000008447 perception Effects 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 claims description 4
- 238000007726 management method Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 230000002401 inhibitory effect Effects 0.000 abstract 1
- 230000004927 fusion Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 229920000049 Carbon (fiber) Polymers 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000004917 carbon fiber Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to an underground space detection system based on an unmanned aerial vehicle, which is based on an unmanned aerial vehicle hardware platform and comprises an underground space autonomous navigation system, a visual identification system, an active disturbance rejection intelligent flight control system, an unmanned aerial vehicle obstacle avoidance system and an information processing platform, wherein the active disturbance rejection intelligent flight control system is based on an integral sliding mode control algorithm of a double-power approach law and an active disturbance rejection intelligent control algorithm based on an adaptive neural network, and the flight path and the flight angle of the unmanned aerial vehicle are adjusted through an extended state observer, so that stable flight and path tracking of the underground space are realized. Compared with the prior art, the unmanned aerial vehicle autonomous navigation method has the advantages of improving the accuracy of a detection target and the adaptability of a special visual environment, effectively inhibiting the buffeting problem generated in the sliding mode control process, improving the accuracy of autonomous navigation of the unmanned aerial vehicle and the like.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle control, in particular to an underground space detection system based on an unmanned aerial vehicle.
Background
Unmanned Aerial vehicle (uav), a special aircraft, can perform various motions according to a preset track without human manipulation. In the flying process, the flying position and the flying attitude of the unmanned aerial vehicle are controlled by collecting and processing various data in the flying motion by a microprocessor and various sensors carried by the body and outputting an adjusting instruction to a power system. With the rapid development of microelectronic technology and computer technology, the size of the unmanned aerial vehicle is continuously reduced, so that the unmanned aerial vehicle can move more flexibly during flight mission; unmanned aerial vehicle's performance constantly promotes for unmanned aerial vehicle self can have faster speed to data processing under the condition that does not rely on the mainframe computer, can accomplish more complicated task.
The underground space detection technology can efficiently carry out underground space surveying and mapping, promote the development and utilization of the underground space, realize the automatic underground detection and enhance the underground military operation capability. Considering that the underground terrain space has complexity and guarantees the high efficiency of detection, it is an optimal scheme to choose an unmanned aerial vehicle to carry out the underground space detection. But the problems of insufficient precision and accuracy exist in the aspects of typical target identification, target picture capture and position calculation.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an underground space detection system based on an unmanned aerial vehicle, which can automatically navigate, avoid obstacles, fly and return in underground spaces such as subways, tunnels, pipe galleries and the like, form a three-dimensional structure for space survey and drawing, and automatically detect, identify and locate typical targets in the space survey and drawing.
The purpose of the invention can be realized by the following technical scheme:
the utility model provides an underground space detecting system based on unmanned aerial vehicle, is based on unmanned aerial vehicle hardware platform, underground space detecting system includes underground space autonomous navigation system, visual identification system, auto-disturbance rejection intelligence flight control system, unmanned aerial vehicle keeps away barrier system and information processing platform, the auto-disturbance rejection intelligence flight control system is based on the integral sliding mode control algorithm of double power law of approach and the auto-disturbance rejection intelligence control algorithm based on adaptive neural network, through the flight path and the flight angle of expansion state observer adjustment unmanned aerial vehicle, realizes the stable flight and the path tracking of underground space.
The underground space autonomous navigation system adopts a V-LOAM algorithm based on deep learning and integrating a laser radar and a binocular vision depth camera.
Furthermore, the underground space autonomous navigation system realizes autonomous navigation of the underground unmanned aerial vehicle through instant positioning, a visual laser radar mapping technology, motion decision and motion planning.
The visual identification system adopts an unmanned aerial vehicle visual algorithm based on artificial intelligence and a convolutional neural network.
Furthermore, the visual recognition system realizes automatic detection and typical target recognition of the underground unmanned aerial vehicle through the infrared sensor and the binocular visual camera.
Furthermore, the visual recognition system is also provided with a particle filter algorithm, and the typical target is positioned and grabbed through the combination of the V-LOAM algorithm and the particle filter algorithm.
The unmanned aerial vehicle obstacle avoidance system adopts an algorithm based on a Laplace artificial potential field.
Furthermore, the unmanned aerial vehicle obstacle avoidance system combines a boundary element method and a map model to complete unmanned aerial vehicle path planning and obstacle avoidance control.
The hardware platform of the unmanned aerial vehicle comprises an unmanned aerial vehicle body, a flight control computer, a perception and task management computer, an environment perception sensor and a networking link, wherein the unmanned aerial vehicle body comprises a rack, a power system and a distribution board.
Further, the frame is made of all-carbon fiber light materials.
The unmanned aerial vehicle fuselage adopts the battery to provide electric power support for each system among the underground space detection system, and is equipped with the stand-by battery on the unmanned aerial vehicle fuselage and can provide electric power support for unmanned aerial vehicle back journey in its maximum continuation of the journey mileage.
The information processing platform is respectively connected with the underground space autonomous navigation system, the vision recognition system, the active disturbance rejection intelligent flight control system and the unmanned aerial vehicle obstacle avoidance system, receives signals sent by sensors in the systems, integrates and stores the information, is provided with an alarm system, and can trigger the alarm system to give an alarm if a certain system cannot work normally.
Compared with the prior art, the invention has the following beneficial effects:
1. the autonomous navigation system for the underground space adopts the laser radar and vision combined navigation, effectively overcomes the complexity of the underground space and improves the accuracy of autonomous navigation of the unmanned aerial vehicle compared with the traditional task that the autonomous navigation can not be well completed by relying on pure vision or pure laser radar navigation.
2. The visual identification system realizes the fusion technology of the laser radar and the binocular RGB-D camera, improves the accuracy of the detected target and the adaptability of the special visual environment, and adopts the unmanned aerial vehicle visual algorithm based on artificial intelligence and a convolutional neural network to realize target detection and target identification; and the positioning of the target and the grabbing of the target are completed through the combination of the V-LOAM process and the particle filter algorithm.
3. According to the active disturbance rejection intelligent flight control system, the integral sliding mode controller based on the double-power approach law is adopted, and the sliding mode control and the double-power approach law are combined, so that the steady-state response of the control system is enhanced, the control precision is improved, and the buffeting problem generated in the sliding mode control process is effectively restrained.
4. The unmanned aerial vehicle obstacle avoidance system realizes motion planning by adopting a Laplace-based artificial potential field algorithm, ensures a convergence global optimal solution by utilizing the construction of the Laplace artificial potential field in an environment map constructed in the SLAM process, completes optimal path planning, and effectively guides the unmanned aerial vehicle to carry out obstacle avoidance control.
Drawings
FIG. 1 is a schematic structural view of the present invention;
fig. 2 is a basic structure of a hardware platform of the unmanned aerial vehicle in the embodiment of the present invention;
FIG. 3 is a block diagram of a deep learning based multi-sensor fusion SLAM system in an embodiment of the present invention;
FIG. 4 is an overall flowchart of a target detection and tracking algorithm based on laser radar and vision sensor information fusion in an embodiment of the present invention;
FIG. 5 is a flow chart of target tracking and positioning based on a particle filtering algorithm in an embodiment of the present invention;
fig. 6 is a flow chart of obstacle avoidance for an unmanned aerial vehicle according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an embodiment of the invention in which the drone flies in "X mode".
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Examples
The main indexes achieved by the unmanned aerial vehicle underground space detection system comprise that the range of a passable space section is 0.8m multiplied by 0.8 m-10 m multiplied by 10 m; the spatial resolution is less than or equal to 0.1m, the relative position precision is less than or equal to 1m, and the relative angle precision is less than or equal to 5 degrees in the mapping precision; the minimum size of the target capable of being detected is 0.05 m; the recognition probability of the personnel target within the distance of 10m is more than or equal to 90 percent; the method has the front-end real-time processing capabilities of typical target identification, target picture capture, position calculation and the like.
As shown in fig. 1, an underground space detection system based on an unmanned aerial vehicle is based on an unmanned aerial vehicle hardware platform, and comprises an underground space autonomous navigation system, a visual identification system, an active disturbance rejection intelligent flight control system, an unmanned aerial vehicle obstacle avoidance system and an information processing platform, wherein the active disturbance rejection intelligent flight control system is based on an integral sliding mode control algorithm of a double-power approach law and an active disturbance rejection intelligent control algorithm based on an adaptive neural network, and the flight path and the flight angle of the unmanned aerial vehicle are adjusted through an extended state observer, so that stable flight and path tracking of the underground space are realized.
The underground space autonomous navigation system adopts a deep learning-based V-LOAM algorithm which integrates a laser radar and a binocular vision depth camera, and realizes autonomous navigation of the underground unmanned aerial vehicle through instant positioning, a vision laser radar mapping technology, motion decision and motion planning.
As shown in fig. 3, a block diagram of a deep learning based multisensor (VL) fusion SLAM system is shown. In view of the fact that both laser SLAM and visual SLAM have certain defects, the problem of underground space autonomous navigation of the unmanned aerial vehicle cannot be effectively solved, in the embodiment, a multi-sensor fusion SLAM solution scheme for fusing and using a laser (radar) camera and a visual depth (RGB-D) camera is adopted, and meanwhile, a deep learning technology is applied to the SLAM, so that the robustness and the accuracy of the autonomous navigation system are improved.
The visual recognition system adopts an unmanned aerial vehicle visual algorithm based on artificial intelligence and a convolutional neural network, and realizes automatic detection and typical target recognition of the underground unmanned aerial vehicle through an infrared sensor and a binocular visual camera.
As shown in fig. 4, it is an overall flowchart of the target detection and tracking algorithm based on the information fusion of the lidar and the vision sensor. In this embodiment, adopt the multisensor to fuse, target detection and tracking algorithm based on laser radar and vision sensor information fusion solves four rotor unmanned aerial vehicle automatic detection and identification problem. Under an initial state, detecting an underground space by using point cloud data of a laser radar, extracting a space internal region according to the reflectivity of the point cloud data, and detecting and identifying a target object on the space internal region by using a Faster R-CNN algorithm; projecting the obstacles detected by the laser radar on a picture according to the calibration information of the existing laser radar and the existing visual sensor, and determining a tracking target according to the color histogram information of the target; on the basis of a particle filtering algorithm, the target position is corrected by utilizing the laser radar point cloud data, so that the target is tracked and positioned.
The visual recognition system is also provided with a particle filter algorithm, and the typical target is positioned and grabbed through the combination of the V-LOAM algorithm and the particle filter algorithm.
Fig. 5 is a flowchart of target tracking and positioning based on particle filter algorithm. In the embodiment, the target tracking algorithm based on the laser radar and the camera is mainly based on a framework of a particle filter algorithm, an initial tracking target is determined by a target detected in a Faster R-CNN algorithm, the target is tracked in an image by using color information, and after particle resampling, the target state is corrected by using a point cloud target detection result of a current frame, so that a more accurate target state is obtained.
The unmanned aerial vehicle obstacle avoidance system adopts an algorithm based on a Laplace artificial potential field, and completes unmanned aerial vehicle path planning and obstacle avoidance control by combining a boundary element method and a map model.
As shown in fig. 6, a flow chart for obstacle avoidance of the unmanned aerial vehicle is shown. The Laplace artificial potential field algorithm is out of the way of the traditional artificial potential field method, and the method is focused on finding a way for solving the inherent defects of the traditional method and has higher practicability and reliability in practical application. The Laplace artificial potential field can be established on a map (such as a point cloud) scanned and reconstructed by a laser radar sensor, the Laplace artificial potential field is different from a traditional artificial potential field, the boundary and the position of an obstacle are described more accurately in the mode, the path planning and flight safety of the unmanned aerial vehicle in a complex environment can be guaranteed, and the method is more suitable for being expanded to the aspect of real-time detection and planning. Compared with search algorithms such as a dynamic window algorithm, a fuzzy logic algorithm, a Bug algorithm, a genetic algorithm, a traditional artificial potential field and the like, the Laplace artificial potential field fundamentally avoids the problem of trapping in a local optimal solution, and ensures convergence to a global optimal solution.
As shown in fig. 2, the hardware platform of the unmanned aerial vehicle comprises an unmanned aerial vehicle body, a flight control computer, a perception and task management computer, an environment perception sensor and a networking link, wherein the unmanned aerial vehicle body comprises a rack, a power system and a distribution board, and the rack is made of a light all-carbon fiber material, specifically a quad-rotor unmanned aerial vehicle.
As shown in fig. 7, in the present embodiment, the drone flies in "X mode" and has a cross section of 0.8 × 0.8m to 10 × 10m, and in consideration of the minimum cross section to be passed of 0.8 × 0.8m, the present embodiment designs the wheelbase of the drone to 643mm after considering the safety distance. The unmanned aerial vehicle adopts an X mode, the maximum length of the unmanned aerial vehicle is 883mm after the unmanned aerial vehicle comprises the blades, and the calculated length of the outermost periphery of the unmanned aerial vehicle is
May pass through the smallest cross-section.
The unmanned aerial vehicle fuselage adopts the battery to provide electric power support for each system among the underground space detection system, and is equipped with the stand-by battery on the unmanned aerial vehicle fuselage and can provide electric power support for unmanned aerial vehicle back journey in its maximum continuation of the journey mileage.
In this embodiment, the three-dimensional lidar of the unmanned aerial vehicle uses Livox's Horizon lidar, and it has characteristics such as far-range, high accuracy, wide angle of view, high reliability and self-adaptation environment. According to the surveying and mapping precision in the main indexes, the spatial resolution is required to be less than or equal to 0.1m, the relative position precision is required to be less than or equal to 1m, and the relative angle precision is required to be less than or equal to 5 degrees. The spatial resolution, i.e. the ground resolution, refers to the field size of the minimum target that can be resolved by the remote sensing instrument, i.e. the size of the ground range corresponding to one pixel on the remote sensing image. The range of the Horizon laser radar can be detected to be 260 meters, the range precision is 2 centimeters, the angle precision is 0.05 degrees, the view field angle is 81.7 degrees multiplied by 25.1 degrees, and the temperature range is-40 ℃ to 85 ℃. It can be seen that the Horizon lidar can meet all of the mapping accuracies in the main index.
The information processing platform is respectively connected with the underground space autonomous navigation system, the vision recognition system, the active disturbance rejection intelligent flight control system and the unmanned aerial vehicle obstacle avoidance system, receives signals sent by the sensors in the systems, integrates and stores the information, is provided with an alarm system, and can trigger the alarm system to give an alarm if a certain system cannot work normally.
In addition, it should be noted that the specific embodiments described in the present specification may have different names, and the above descriptions in the present specification are only illustrations of the structures of the present invention. All equivalent or simple changes in the structure, characteristics and principles of the invention are included in the protection scope of the invention. Various modifications or additions may be made to the described embodiments or methods may be similarly employed by those skilled in the art without departing from the scope of the invention as defined in the appending claims.
Claims (10)
1. The utility model provides an underground space detecting system based on unmanned aerial vehicle, its characterized in that, based on unmanned aerial vehicle hardware platform, underground space detecting system includes underground space autonomous navigation system, visual identification system, active disturbance rejection intelligence flight control system, unmanned aerial vehicle keeps away barrier system and information processing platform, the active disturbance rejection intelligence flight control system is based on the integral sliding mode control algorithm of double power approach law and the active disturbance rejection intelligence control algorithm based on adaptive neural network, through the flight path and the flight angle of expansion state observer adjustment unmanned aerial vehicle, realizes the stable flight and the path tracking in underground space.
2. The unmanned aerial vehicle-based underground space exploration system of claim 1, wherein said underground space autonomous navigation system employs a deep learning-based V-loop algorithm that combines lidar and binocular vision depth cameras.
3. The underground space exploration system based on unmanned aerial vehicle as claimed in claim 2, wherein said underground space autonomous navigation system realizes underground unmanned aerial vehicle autonomous navigation through instant positioning, visual lidar mapping technology, motion decision and motion planning.
4. An unmanned aerial vehicle-based underground space detection system as claimed in claim 2, wherein the vision recognition system employs an unmanned aerial vehicle vision algorithm based on artificial intelligence and a convolutional neural network.
5. The underground space detection system based on the unmanned aerial vehicle as claimed in claim 4, wherein the vision recognition system realizes automatic detection and recognition of typical targets by the underground unmanned aerial vehicle through an infrared sensor and a binocular vision camera.
6. An unmanned aerial vehicle-based underground space detection system according to claim 5, wherein the vision recognition system is further provided with a particle filter algorithm, and the positioning and grabbing of the typical target are completed through the combination of a V-LOAM algorithm and the particle filter algorithm.
7. An unmanned aerial vehicle-based underground space detection system as claimed in claim 1, wherein the unmanned aerial vehicle obstacle avoidance system employs an algorithm based on a laplacian artificial potential field.
8. An unmanned aerial vehicle-based underground space detection system as claimed in claim 7, wherein the unmanned aerial vehicle obstacle avoidance system combines a boundary element method and a map model to complete unmanned aerial vehicle path planning and obstacle avoidance control.
9. An unmanned aerial vehicle-based underground space detection system as claimed in claim 1, wherein the hardware platform of the unmanned aerial vehicle comprises an unmanned aerial vehicle body, a flight control computer, a perception and task management computer, an environment perception sensor and a networking link, and the unmanned aerial vehicle body comprises a frame, a power system and a distribution board.
10. The underground space detection system based on the unmanned aerial vehicle as claimed in claim 1, wherein the information processing platform is connected with the underground space autonomous navigation system, the vision recognition system, the active disturbance rejection intelligent flight control system and the unmanned aerial vehicle obstacle avoidance system respectively, receives signals sent by sensors in the systems, integrates and stores information, and an alarm system is arranged in the information processing platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110319716.8A CN113093792A (en) | 2021-03-25 | 2021-03-25 | Underground space detection system based on unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110319716.8A CN113093792A (en) | 2021-03-25 | 2021-03-25 | Underground space detection system based on unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113093792A true CN113093792A (en) | 2021-07-09 |
Family
ID=76669744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110319716.8A Pending CN113093792A (en) | 2021-03-25 | 2021-03-25 | Underground space detection system based on unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113093792A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007088225A1 (en) * | 2006-01-31 | 2007-08-09 | Universidad Politécnica de Madrid | Computer vision system for picking small row-cultivated fruits |
| CN105700542A (en) * | 2016-03-30 | 2016-06-22 | 北京航空航天大学 | Stratosphere airship control and distribution method based on vector field guidance and least square method |
| CN106052695A (en) * | 2016-07-14 | 2016-10-26 | 上海工程技术大学 | Flight inspection tour system and method performing navigation by utilizing 360-degree laser scanner |
| CN111522358A (en) * | 2020-04-23 | 2020-08-11 | 河南鼎健航天技术股份有限公司 | Unmanned aerial vehicle dynamic obstacle avoidance method |
| CN111796602A (en) * | 2020-06-18 | 2020-10-20 | 江苏大学 | Plant protection unmanned aerial vehicle barrier is surveyed and early warning system |
-
2021
- 2021-03-25 CN CN202110319716.8A patent/CN113093792A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007088225A1 (en) * | 2006-01-31 | 2007-08-09 | Universidad Politécnica de Madrid | Computer vision system for picking small row-cultivated fruits |
| CN105700542A (en) * | 2016-03-30 | 2016-06-22 | 北京航空航天大学 | Stratosphere airship control and distribution method based on vector field guidance and least square method |
| CN106052695A (en) * | 2016-07-14 | 2016-10-26 | 上海工程技术大学 | Flight inspection tour system and method performing navigation by utilizing 360-degree laser scanner |
| CN111522358A (en) * | 2020-04-23 | 2020-08-11 | 河南鼎健航天技术股份有限公司 | Unmanned aerial vehicle dynamic obstacle avoidance method |
| CN111796602A (en) * | 2020-06-18 | 2020-10-20 | 江苏大学 | Plant protection unmanned aerial vehicle barrier is surveyed and early warning system |
Non-Patent Citations (7)
| Title |
|---|
| JI ZHANG: "Visual-lidar Odometry and Mapping: Low-drift, Robust, and Fast", 《ICRA》 * |
| 刘树春: "《深度实践OCR基于深度学习的文字识别》", 31 May 2020 * |
| 吕超: "《空中机器人规划与决策》", 28 February 2018 * |
| 孟宪宇: "《多感知系统与智能仿真》", 30 June 2012 * |
| 杨兴明: "基于滑模控制器的四旋翼飞行器控制", 《合肥工业大学学报》 * |
| 罗钉: "《机载有源相控阵火控雷达技术》", 31 January 2018 * |
| 陈宗海: "《系统仿真技术及其应用第18卷》", 31 August 2017 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111932588B (en) | Tracking method of airborne unmanned aerial vehicle multi-target tracking system based on deep learning | |
| CN206691107U (en) | Pilotless automobile system and automobile | |
| Luo et al. | A survey of intelligent transmission line inspection based on unmanned aerial vehicle | |
| US8718838B2 (en) | System and methods for autonomous tracking and surveillance | |
| CN107161141A (en) | Pilotless automobile system and automobile | |
| CN105759834A (en) | System and method of actively capturing low altitude small unmanned aerial vehicle | |
| WO2010129907A2 (en) | Method and system for visual collision detection and estimation | |
| CN112596071A (en) | Unmanned aerial vehicle autonomous positioning method and device and unmanned aerial vehicle | |
| Singh et al. | Comparative analysis of range sensors for the robust autonomous navigation–a review | |
| CN112378397B (en) | Unmanned aerial vehicle target tracking method and device and unmanned aerial vehicle | |
| CN111679695A (en) | Unmanned aerial vehicle cruising and tracking system and method based on deep learning technology | |
| CN115933754A (en) | Electric power inspection unmanned aerial vehicle obstacle avoidance method based on millimeter wave radar and binocular vision | |
| Liu et al. | A survey on sensor technologies for unmanned ground vehicles | |
| Savva et al. | ICARUS: Automatic autonomous power infrastructure inspection with UAVs | |
| Zhahir et al. | Current development of UAV sense and avoid system | |
| CN109801484A (en) | A kind of emergency communication UAV system and emergency communication system | |
| CN112380933B (en) | Unmanned aerial vehicle target recognition method and device and unmanned aerial vehicle | |
| KR102289752B1 (en) | A drone for performring route flight in gps blocked area and methed therefor | |
| Bhanu et al. | A system for obstacle detection during rotorcraft low altitude flight | |
| Cheng et al. | Integration of active and passive sensors for obstacle avoidance | |
| Kamat et al. | A survey on autonomous navigation techniques | |
| Rydell et al. | Autonomous UAV-based forest mapping below the canopy | |
| CN113093792A (en) | Underground space detection system based on unmanned aerial vehicle | |
| Stambler et al. | Detection and reconstruction of wires using cameras for aircraft safety systems | |
| CN117554989A (en) | Visual fusion laser radar SLAM positioning navigation method and unmanned aerial vehicle system thereof |
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: 20210709 |