CN113311848A - Underwater detector and surrounding edge obstacle avoidance method thereof - Google Patents
Underwater detector and surrounding edge obstacle avoidance method thereof Download PDFInfo
- Publication number
- CN113311848A CN113311848A CN202110480581.3A CN202110480581A CN113311848A CN 113311848 A CN113311848 A CN 113311848A CN 202110480581 A CN202110480581 A CN 202110480581A CN 113311848 A CN113311848 A CN 113311848A
- Authority
- CN
- China
- Prior art keywords
- detector
- obstacle avoidance
- obstacle
- underwater
- distance measuring
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 230000005484 gravity Effects 0.000 claims abstract description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 8
- 230000009182 swimming Effects 0.000 claims description 4
- 230000008054 signal transmission Effects 0.000 claims description 3
- 239000000523 sample Substances 0.000 claims 1
- 241000251468 Actinopterygii Species 0.000 description 57
- 238000010586 diagram Methods 0.000 description 6
- 239000011664 nicotinic acid Substances 0.000 description 6
- 230000001788 irregular Effects 0.000 description 5
- 108010066057 cabin-1 Proteins 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012876 topography Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 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
- G05D1/04—Control of altitude or depth
- G05D1/06—Rate of change of altitude or depth
- G05D1/0692—Rate of change of altitude or depth specially adapted for under-water vehicles
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)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an underwater detector which comprises a main engine cabin, a control cabin and tail fins, wherein a left infrared distance measuring sensor, a middle infrared distance measuring sensor and a right infrared distance measuring sensor are arranged below a camera in front of the main engine cabin and are used for detecting sector areas in the left front, the right front and the right front respectively; a gravity center adjusting device is arranged in the main engine room and used for adjusting the gravity center of the detector according to the posture of the detector; the control cabin controls the tail fin to swing according to the detection result, and power for advancing and steering the detector is provided; the invention also discloses a surrounding obstacle avoidance method of the underwater detector, which is characterized in that the surrounding obstacle avoidance is realized by calculating and controlling the swing amplitude and speed of the tail fin according to the real-time information of the left infrared detection, the middle infrared detection and the right infrared detection and combining with the fuzzy control rule. According to the underwater detector, under the surrounding obstacle avoidance method, the advancing direction and speed are calculated and adjusted based on a plurality of infrared detection results, and the obstacle avoidance accuracy is high and the real-time performance is strong; after obstacle avoidance, the advancing direction is adjusted to keep close-to tour, and targets at underwater boundaries and boundaries are explored more comprehensively.
Description
Technical Field
The invention relates to an underwater detector and a surrounding edge obstacle avoidance method thereof, and belongs to the field of underwater path detection.
Background
With the progress of sensors, computers and intelligent control technologies and the increasing development of marine economy, research and development of underwater robots are gradually valued by scientists. The bionic robot fish has the advantages of long working time, large movement range, capability of working in an underwater environment with higher requirements on mobility and the like, and can efficiently carry out a plurality of works such as submarine exploration, marine organism observation, marine organism investigation, marine life saving and the like; the premise of underwater work of the bionic robot fish is that the bionic robot fish has autonomous navigation and obstacle avoidance capabilities, and therefore the path planning problem is an important research direction for researchers. The path planning of the robot fish is to seek a feasible path from a starting point to a target point under certain barrier environmental conditions, so that the robot fish can safely reach the designated position without collision.
However, if the underwater topography is unknown, how to better enable operators to quickly know the underwater topography structure is convenient for subsequent operation is a problem, and the most important purpose for knowing the underwater topography structure is to search boundaries in various underwater directions; on the other hand, due to the existence of water waves and the continuous movement of water bottom water flow, a lot of objects needing to be explored are accumulated at the underwater boundary, a lot of underwater operations need operators or robotic fish to be tightly attached to the water bottom of a bank, and how to enable the robotic fish to avoid obstacles and simultaneously to tour and record around the underwater boundary is a problem with research value.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide an underwater detector and a surrounding obstacle avoidance method thereof, which can explore an underwater boundary and comprehensively and accurately detect and identify a target object at the boundary while avoiding obstacles autonomously.
The technical scheme is as follows: the underwater detector comprises a main engine room, a control room, a battery room and tail fins, wherein a left infrared distance measuring sensor, a middle infrared distance measuring sensor and a right infrared distance measuring sensor are arranged below a camera in front of the main engine room and are used for respectively detecting the distance between obstacles right in front of the detector and between obstacles on the left front and the right front; the tail fin provides power for advancing and steering the detector.
And the bottom of the main cabin is also provided with a pressure sensor for measuring and recording water pressure.
The main cabin further comprises a signal transmission antenna used for externally sending measured water pressure information and pictures shot when the detector patrols and avoids obstacles.
The distance measured by the infrared distance measuring sensor is 7-40cm in front of the sensor.
The surrounding edge obstacle avoidance method of the underwater detector comprises the following steps:
a) the initial welting flag bit of the detector is 0, and the detector moves forward and straight in water;
b) judging whether an obstacle exists or reaches a boundary in the advancing direction according to a distance measurement result fed back by the infrared distance measurement sensor;
c) if the obstacle is judged to exist or the obstacle is reached, switching the action state of the detector into an obstacle avoidance state, switching the welting mark bit from 0 to 1, calculating the speed and the steering angle which should be reduced according to the distance of the obstacle and a fuzzy control rule, controlling the detector to decelerate and turn right, photographing and storing the front environment through a front camera, switching the action state of the detector into a tour state when the infrared distance measuring sensor on the left side detects that the distance of the obstacle or the boundary is greater than an obstacle avoidance warning value L, switching the welting mark bit from 1 to 0, calculating the steering angle of the detector according to the infrared measuring result on the left side and the fuzzy control rule, controlling the detector to deflect left, and performing welting tour;
d) if no obstacle is judged or the boundary is not reached, the detector keeps a close-side tour state and accelerates straight tour.
When the welting flag bit is 0, the detector accelerates forward and moves straight; when the welting flag is 1, the detector performs a left welting action.
Further, in step c, the deceleration algorithm is:
wherein V is the speed of the detector before obstacle avoidance, V1For the speed of the detector during turning, L1, L2 and L3 are the distances from the obstacle or boundary measured by the left, middle and right infrared distance measuring sensors, respectively.
Further, in step c, the steering angle algorithm is as follows:
wherein Q is1For detector right deflection angle, Q2Setting the amplitude of the tail fin swing to be 0-180 degrees for the left deflection angle of the detector, and setting the corresponding radian to be 0-pi.
In the process of switching the obstacle avoidance state into the welting tour state, the leftward inclination angle of the detector is fixed to be 30 degrees, namely the middle axis of the fishtail is positioned at 120 degrees.
Has the advantages that: compared with the prior art, the invention has the following remarkable advantages: based on a fuzzy control rule and a measurement result of a distance measurement sensor, the amplitude, the angle and the speed of the swing of the tail fin are controlled by a motor to adjust the traveling direction and the speed so as to avoid the obstacle, and the obstacle avoidance accuracy is high and the real-time performance is strong; and (4) moving along the border, adjusting the moving direction in time, and exploring and identifying the underwater boundary and the target object at the boundary more comprehensively.
Drawings
FIG. 1 is a schematic view of an underwater detector;
FIG. 2 is a flow chart of edge-around obstacle avoidance;
FIG. 3 is a schematic diagram of a path of a conventional obstacle avoidance method in a pool with a regular boundary;
FIG. 4 is a schematic diagram of a path in a pool with a regular boundary according to the edge-around obstacle avoidance method of the present invention;
FIG. 5 is a schematic diagram of a conventional obstacle avoidance method for a path in an irregular boundary pool;
fig. 6 is a schematic diagram of a path of the edge-surrounding obstacle avoidance method in an irregular boundary pool.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, the underwater vehicle of the present invention is preferably a robotic fish, and includes a main nacelle 1, a battery compartment 2, a control compartment 3, and a tail fin 4. And a gravity center adjusting device is arranged in the control cabin 1, and the gravity center position can be automatically adjusted according to the self posture. When the robot fish is under the action of surge and the posture of the robot fish inclines, the automatic adjusting device immediately performs corresponding gravity center adjusting action, so that the stability of the posture of the robot fish is kept; the bottom of the main cabin 1 is also provided with a pressure sensor 104 for measuring and recording water pressure, and the top of the main cabin 1 also comprises a signal transmission antenna 101 for sending measured water pressure information to the outside and pictures shot by a detector during tour and obstacle avoidance; the tail fin 4 is driven to swing through a control motor in the control cabin 3, the moving speed and the moving direction of the robot fish are adjusted, the position where the fish tail stops after starting is determined by the median value of a fish tail steering engine, the angle of the fish tail is divided into 0-180 degrees, and the normal median value of the fish tail is generally close to 90 degrees. Wherein, the larger the numerical value is, the more leftwards the arranged fish tail (looking towards the fish head from the fish tail direction); the principle of the median value of the heeling steering engine and the pitching steering engine is the same as that of the fishtail steering engine.
Three infrared Distance measuring sensors 103 are arranged below the camera 102 in front of the main cabin 1, and are respectively a left small infrared ray, a right small infrared ray and a middle large infrared ray, which are defined as g _ InfraredLeft, g _ InfraredRight and g _ Distance. The left infrared and the right infrared are respectively detected obliquely to the left front and the right front, and are not detected vertically and forwards like the middle infrared, and the detection directions of the three infrared are integrally in a fan shape; the value fed back by the left and right infrared sensors when no object exists in the front is 680 (mm), and due to the limitation of the size of the robotic fish in the embodiment of the invention, the selected infrared sensors have an effective detection distance interval of 7-40 cm; the angle corresponding to the camera is defined as Encode, and by combining a PID control algorithm, lens shaking caused by movement of the robot fish body can be effectively reduced, and the accuracy of image recognition is improved.
The path planning mainly includes local path planning and global path planning. The global path planning is that the model motion environment is fixed and invariable, and the obstacles are static and position invariable. Local path planning is planning for a certain unknown area. Because the swimming underwater environment and the application scene of the bionic robot fish are different according to specific conditions, the path planning of the bionic robot fish adopts local path planning. The local path planning mainly includes an artificial potential field method, a fuzzy logic method, a neural network method, a genetic algorithm and the like. The fuzzy logic algorithm is characterized in that: people often describe objects in their daily lives where the boundary partitions are not very clear in fuzzy language. Then fuzzy judgment and reasoning are carried out through the brain. The fuzzy logic method belongs to one of the methods of artificial intelligence. It does not need to establish an accurate mathematical model, and describes independent variables and dependent variables and the relation between the independent variables and the dependent variables by using a nearly natural language.
Based on the above characteristics, for the circular border tour obstacle avoidance of the unknown water area, the embodiment of the invention adopts a fuzzy logic algorithm, and the flow chart is shown in fig. 2.
Specifically, the edge-surrounding obstacle avoidance method comprises the following steps:
a) judging whether an obstacle exists in front of the robot fish in the traveling direction (or whether the robot fish reaches a boundary) according to measurement results fed back by the three infrared distance measuring sensors at the two sides and the middle;
the feedback values of the three infrared sensors are respectively compared with the obstacle avoidance warning value L to obtain the conditions listed in the following table:
because the left infrared and the right infrared are obliquely detected to the left front and the right front respectively, and the middle infrared detected vertically forwards is combined, the detection range of the three infrared detectors is a front fan-shaped area. This is the reason why the value measured by the middle infrared in the second line of data is further less than the warning value than the left and right infrared, and also is to trigger the ring edge flag position 1 when the value measured by the left infrared is less than the warning value after the right turn, so as to prevent the detector from further moving away from the boundary. The comparison result of the measurement values of the first row and the fourth row in the table is the same, but the judgment result is different, namely the advancing program of the detector is different because of the difference of the initial surrounding zone bits, namely the detector in the first row is in a straight-going state, and the detector in the fourth row is in a left-turning welting state.
According to the comparison condition in the table, the robot fish makes corresponding selection;
b) if the robot fish is judged to know that the robot fish has an obstacle (or reaches a boundary) in the advancing direction, the robot fish enters an obstacle avoidance state, the speed and the turning angle which are required to be reduced by the robot fish are obtained according to the distance of the obstacle and a fuzzy control rule, then the robot fish is decelerated and turns to the right, and meanwhile, the robot fish is photographed by a front camera and uploaded to an upper computer for storage; the robot fish keeps an obstacle avoidance state, the welting mark position is set to be 1 from 0 until the infrared distance measuring sensor on the left side is larger than an obstacle avoidance warning value L of the robot fish, the robot fish enters a welting tour state, meanwhile, the welting mark position is set to be 0 from 1, the turning angle of the robot fish is obtained according to the measurement result of infrared feedback on the left side and a fuzzy control rule, then the robot fish is deflected leftwards at a small angle and is waited tour, and if the distance between the robot fish and a boundary is small or an obstacle is judged again in front of the robot fish (or the robot fish reaches the boundary), the obstacle avoidance function is continuously triggered;
c) if the robot fish is judged and known to have no obstacle (or not reach the boundary) in the traveling direction, the robot fish accelerates to move straight, and the boundary needing to move around and the target needing to be identified are searched.
When the welting flag bit is 0, the detector accelerates forward and moves straight; when the welting flag is 1, the detector performs a left welting action.
The speed of the robot fish before obstacle avoidance is setIs V, the unit is cm/s, and the speed of the robot fish during the deceleration turning is set as V1Then, the deceleration algorithm adopted by the invention is as follows:
the algorithm is such that the closer the robotic fish is to the obstacle or boundary, the greater the magnitude of deceleration and the slower the swimming speed.
The turning angle of the robotic fish is determined by the fish tail deflection value and the swimming speed of the robotic fish, the fish tail angle is divided into 0-180 degrees, and the normal fish tail median value is generally around 90 degrees. Wherein, the larger the numerical value is, the more leftwards the arranged fish tail (looking towards the fish head from the fish tail direction), the median value of the fish tail of the robot fish at the S2 stage is set as pi/2, and the angles of the right deviation and the left deviation at the S3 stage are respectively set as Q1、Q2In the step S3, the turning angle algorithm adopted in the present invention is:
in the algorithm, the closer the robotic fish is to the obstacle or boundary, the larger the turning angle is; when the obstacle avoidance state is switched to the close-side tour state, the left deflection angle is 30 degrees, which corresponds to 120 degrees of the median value of the fishtail.
Further, the specific experimental effects of the embodiment of the present invention for testing the above algorithm are shown in fig. 3 to 6.
Fig. 3 is a schematic diagram of a path of a conventional obstacle avoidance method in a pool with a regular boundary, and fig. 4 is a schematic diagram of a path of a surrounding obstacle avoidance method in a pool with a regular boundary.
Specifically, as shown in fig. 3, in the regular pool, although the normal obstacle avoidance and target identification algorithm effectively completes the obstacle avoidance process, the target object cannot be identified in the whole first-stage tour; as shown in fig. 4, the multi-angle sensor circular border tour algorithm of the invention not only effectively completes obstacle avoidance, but also can circularly tour around the boundary of the regular pool, completes the detection task for the target object concentrated at the boundary of the pool, successfully identifies the target object, takes a picture through the camera, uploads the picture to the upper computer terminal for storage
Furthermore, the comparison between the irregular pools shown in fig. 5 and fig. 6 is more obvious, as shown in fig. 5, the common obstacle avoidance and target identification algorithm has a large blind area in the field of view, while the algorithm of the present invention applied in fig. 6 effectively completes the detection tasks of obstacle avoidance and target identification at the same time, and has no blind area for various blind areas in the field of view of the irregular pool, so that the target object is successfully identified and photographed by the camera and uploaded to the upper computer for storage.
According to the detection comparison results shown in fig. 3-6, it can be seen that the detection effect of the algorithm of the present invention is significantly improved compared with the detection effect of the existing underwater detection algorithm when the detection of the detector on the underwater boundary and the exploration and identification of the target object at the underwater boundary are controlled, and the specific expression is as follows: the detector using the algorithm can timely adjust the traveling direction again after the direction is adjusted to avoid the obstacle no matter the underwater environment with the regular or irregular boundary, so that the detector keeps close-up tour, and cannot be far away from the boundary due to obstacle avoidance, so that the exploration of the boundary target is omitted, and the technical problem which is not solved by the existing underwater detection algorithm is solved.
According to the underwater circular border tour path planning method for the bionic robot fish, provided by the embodiment of the invention, the deflection angle of the tail fin controlled by the motor is controlled based on the fuzzy control rule and the measurement result of the ranging sensor, so that the obstacle can be avoided in real time, the direction can be adjusted in time, the tail fin is close to the underwater boundary, the problem of a target search and rescue task at the underwater boundary is solved, the method is high in accuracy and strong in real-time performance, and the task background is better targeted.
Claims (9)
1. An underwater detector comprises a main engine room (1), a control room (3) and tail fins (4), and is characterized in that a left infrared distance measuring sensor, a middle infrared distance measuring sensor and a right infrared distance measuring sensor (103) are arranged below a camera (102) in front of the main engine room (1) and are used for detecting sector areas in the left front, the right front and the right front respectively; a gravity center adjusting device is further arranged in the main cabin (1) and used for adjusting the gravity center of the detector according to the posture of the detector; and the control cabin (3) controls the tail fin (4) to swing according to the infrared detection result.
2. Underwater probe according to claim 1, characterized in that the bottom of the main nacelle (1) is also provided with a pressure sensor (104).
3. Subsea controller according to claim 1, characterized in that the main nacelle (1) further comprises a signal transmission antenna (101).
4. A subsea controller in accordance with claim 1, characterized in that the infrared distance measuring sensor (103) detects a distance of 7-40cm in front of the sensor.
5. An edge surrounding obstacle avoidance method for the underwater detector as claimed in any one of claims 1 to 4, characterized by comprising the following steps:
a) the initial welting flag bit of the detector is 0, and the detector moves forward and straight in water;
b) judging whether an obstacle exists or reaches a boundary in the advancing direction according to a distance measurement result fed back by the infrared distance measurement sensor;
c) if the obstacle is judged to exist or the obstacle is reached, switching the detector action state to the obstacle avoidance state, switching the welt zone bit from 0 to 1, calculating the speed and the steering angle to be reduced according to the obstacle distance and the fuzzy control rule, controlling the detector to decelerate and turn right, switching the detector action state to the welt tour state when the infrared distance measuring sensor on the left side detects that the obstacle or the boundary distance is greater than the obstacle avoidance warning value L, switching the welt zone bit from 1 to 0, calculating the steering angle of the detector according to the infrared measuring result on the left side and the fuzzy control rule, controlling the detector to deflect left, and performing welt tour;
d) if no obstacle is judged or the boundary is not reached, the detector keeps a close-side tour state and accelerates straight tour.
6. The underwater surrounding edge obstacle avoidance method according to claim 5, wherein when the welting flag is 0, the detector accelerates forward straight swimming, and when the welting flag is 1, the detector executes left welting.
7. The edge-surrounding obstacle avoidance method according to claim 5, wherein in the step c, the deceleration algorithm is:
wherein V is the speed of the detector before obstacle avoidance, V1For the speed of the detector during turning, L1, L2, and L3 are the distances from the obstacle or boundary measured by the left, middle, and right infrared distance measuring sensors, respectively.
8. The edge-surrounding obstacle avoidance method according to claim 5, wherein in the step c, the steering angle algorithm is as follows:
wherein Q is1For detector right deflection angle, Q2Setting the amplitude range of the swinging of the tail fin to be 0-180 degrees for the left deflection angle of the detector, and setting the corresponding radian to be 0-pi.
9. The method according to claim 5, wherein in the step c, when the obstacle avoidance state is switched to the welt tour state, the leftward inclination angle of the detector is fixed to 30 °.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110480581.3A CN113311848B (en) | 2021-04-30 | 2021-04-30 | Underwater detector and surrounding edge obstacle avoidance method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110480581.3A CN113311848B (en) | 2021-04-30 | 2021-04-30 | Underwater detector and surrounding edge obstacle avoidance method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113311848A true CN113311848A (en) | 2021-08-27 |
| CN113311848B CN113311848B (en) | 2022-12-30 |
Family
ID=77371357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110480581.3A Active CN113311848B (en) | 2021-04-30 | 2021-04-30 | Underwater detector and surrounding edge obstacle avoidance method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113311848B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117590857A (en) * | 2024-01-19 | 2024-02-23 | 南京杰辉智能科技有限公司 | Underwater environment detection method based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104049634A (en) * | 2014-07-02 | 2014-09-17 | 燕山大学 | Intelligent body fuzzy dynamic obstacle avoidance method based on Camshift algorithm |
| CN206218186U (en) * | 2016-11-05 | 2017-06-06 | 杭州畅动智能科技有限公司 | A kind of obstacle avoidance apparatus under water for bionic machine |
| CN206579819U (en) * | 2017-02-28 | 2017-10-24 | 西南民族大学 | A kind of intelligent barrier avoiding machine fish |
| CN110356536A (en) * | 2019-08-21 | 2019-10-22 | 中国科学院自动化研究所 | A kind of bionic machine fish of Environment Oriented monitoring |
| CN112162075A (en) * | 2020-10-21 | 2021-01-01 | 武汉工程大学 | Autonomous navigation bionic robot fish for water quality monitoring and control method thereof |
-
2021
- 2021-04-30 CN CN202110480581.3A patent/CN113311848B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104049634A (en) * | 2014-07-02 | 2014-09-17 | 燕山大学 | Intelligent body fuzzy dynamic obstacle avoidance method based on Camshift algorithm |
| CN206218186U (en) * | 2016-11-05 | 2017-06-06 | 杭州畅动智能科技有限公司 | A kind of obstacle avoidance apparatus under water for bionic machine |
| CN206579819U (en) * | 2017-02-28 | 2017-10-24 | 西南民族大学 | A kind of intelligent barrier avoiding machine fish |
| CN110356536A (en) * | 2019-08-21 | 2019-10-22 | 中国科学院自动化研究所 | A kind of bionic machine fish of Environment Oriented monitoring |
| CN112162075A (en) * | 2020-10-21 | 2021-01-01 | 武汉工程大学 | Autonomous navigation bionic robot fish for water quality monitoring and control method thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117590857A (en) * | 2024-01-19 | 2024-02-23 | 南京杰辉智能科技有限公司 | Underwater environment detection method based on machine vision |
| CN117590857B (en) * | 2024-01-19 | 2024-03-26 | 南京杰辉智能科技有限公司 | Underwater environment detection method based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113311848B (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rohan et al. | Convolutional neural network-based real-time object detection and tracking for parrot AR drone 2 | |
| Eresen et al. | Autonomous quadrotor flight with vision-based obstacle avoidance in virtual environment | |
| Boudjit et al. | Human detection based on deep learning YOLO-v2 for real-time UAV applications | |
| CN104571128B (en) | Underwater robot barrier-avoiding method based on distance with parallax information | |
| CN111399505A (en) | Mobile robot obstacle avoidance method based on neural network | |
| CN105629970A (en) | Robot positioning obstacle-avoiding method based on supersonic wave | |
| CN112928799B (en) | Automatic butt-joint charging method of mobile robot based on laser measurement | |
| Chatterjee et al. | Mobile robot navigation | |
| Hui et al. | A novel autonomous navigation approach for UAV power line inspection | |
| Ji-Yong et al. | Design and vision based autonomous capture of sea organism with absorptive type remotely operated vehicle | |
| CN110427042A (en) | Unmanned plane low latitude barrier-avoiding method based on ultrasonic wave and binocular vision | |
| Guidolini et al. | Handling pedestrians in crosswalks using deep neural networks in the IARA autonomous car | |
| Liu et al. | CNN-based vision model for obstacle avoidance of mobile robot | |
| CN110825108A (en) | Cooperative anti-collision method for multiple tracking unmanned aerial vehicles in same airspace | |
| CN109814565A (en) | The unmanned boat intelligence navigation control method of space-time double fluid data-driven depth Q study | |
| CN113311848B (en) | Underwater detector and surrounding edge obstacle avoidance method thereof | |
| El-Gaaly et al. | Visual obstacle avoidance for autonomous watercraft using smartphones | |
| Durdevic et al. | Vision aided navigation of a quad-rotor for autonomous wind-farm inspection | |
| Yu | Development of real-time acoustic image recognition system using by autonomous marine vehicle | |
| CN112373486A (en) | Unmanned driving method and system for small robot | |
| Chen et al. | A review of autonomous obstacle avoidance technology for multi-rotor UAVs | |
| Abdulazeez et al. | Vision-based mobile robot controllers: a scientific review | |
| CN113721615B (en) | Navigation path planning method and system based on machine vision | |
| CN108748165A (en) | A kind of artificial intelligence robot of autonomous classification anticollision | |
| CN114756033B (en) | Underground water-permeable robot pipeline-following inspection method |
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 |