CN119142491A - High-anti-flow multi-point observation type fish school monitoring underwater robot based on multi-source data fusion - Google Patents
High-anti-flow multi-point observation type fish school monitoring underwater robot based on multi-source data fusion Download PDFInfo
- Publication number
- CN119142491A CN119142491A CN202411658721.1A CN202411658721A CN119142491A CN 119142491 A CN119142491 A CN 119142491A CN 202411658721 A CN202411658721 A CN 202411658721A CN 119142491 A CN119142491 A CN 119142491A
- Authority
- CN
- China
- Prior art keywords
- fish
- ocean current
- underwater robot
- water flow
- sensor
- 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
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 123
- 230000004927 fusion Effects 0.000 title claims abstract description 58
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 104
- 238000013135 deep learning Methods 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 230000033228 biological regulation Effects 0.000 claims abstract description 5
- 238000010248 power generation Methods 0.000 claims description 38
- 238000005516 engineering process Methods 0.000 claims description 26
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 230000033001 locomotion Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 8
- 238000013136 deep learning model Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 abstract 1
- 230000001105 regulatory effect Effects 0.000 abstract 1
- 238000000034 method Methods 0.000 description 16
- 239000013535 sea water Substances 0.000 description 10
- 230000008901 benefit Effects 0.000 description 8
- 238000011084 recovery Methods 0.000 description 8
- 230000009182 swimming Effects 0.000 description 8
- 238000013461 design Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 230000002035 prolonged effect Effects 0.000 description 5
- 230000002441 reversible effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 239000003792 electrolyte Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006722 reduction reaction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63C—LAUNCHING, HAULING-OUT, OR DRY-DOCKING OF VESSELS; LIFE-SAVING IN WATER; EQUIPMENT FOR DWELLING OR WORKING UNDER WATER; MEANS FOR SALVAGING OR SEARCHING FOR UNDERWATER OBJECTS
- B63C11/00—Equipment for dwelling or working underwater; Means for searching for underwater objects
- B63C11/52—Tools specially adapted for working underwater, not otherwise provided for
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/86—Combinations of sonar systems with lidar systems; Combinations of sonar systems with systems not using wave reflection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/96—Sonar systems specially adapted for specific applications for locating fish
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a multi-source data fusion-based high-current-resistance multi-point observation type fish shoal monitoring underwater robot which comprises a shell, a self-adaptive ocean current resistance system and an energy system, wherein the self-adaptive ocean current resistance system comprises an ocean current information detection module and a PID control algorithm real-time regulation and control propeller module, the ocean current information detection module is used for collecting ocean current information in real time, the ocean current information detection module comprises water flow speed, direction and turbulence intensity, the control algorithm real-time regulation and control propeller module is used for regulating and controlling the power and the direction of the propeller in real time according to ocean current change by utilizing the PID control algorithm, the stability of the underwater robot in complex ocean current is ensured, the telescopic multi-sensor fusion system is used for collecting multi-dimensional data of fish shoals by combining a plurality of sensors and carrying out fusion analysis on the data by utilizing a deep learning algorithm, and therefore the high-precision fish shoal identification and tracking are realized, and the integrated ocean current-solar energy system enables the underwater robot to have long-time duration.
Description
Technical Field
The invention belongs to the technical field of underwater robots, and particularly relates to a high-anti-flow multi-point observation type fish school monitoring underwater robot based on multi-source data fusion.
Background
With the rapid development of the fields of aquaculture and marine ecological protection, the monitoring and tracking of fish shoals becomes a key task. However, conventional monitoring means rely on manual operation or static equipment, and it is difficult to meet the high-efficiency monitoring requirements in the complex open sea environment. Especially under the conditions that the open ocean current is complex, the fish shoal moves rapidly and fish individuals overlap, the traditional underwater monitoring equipment is easy to lose stability and insufficient in cruising ability, and the image recognition accuracy is low, so that real-time high-quality data cannot be provided.
The defects and reasons of the prior art are that the traditional underwater robot is easily influenced by water flow in an open sea complex ocean current environment, and the stability of equipment is insufficient, so that the problems of data acquisition distortion and the like are caused. This poses a threat to the continuity of shoal monitoring and research and the accuracy of the data. Aiming at the defects of insufficient image recognition function, difficult image recognition, rapid swimming of the fish shoals and overlapping among individuals, the traditional image recognition algorithm is provided with great challenges, so that the recognition accuracy is low, the error is large, and the individual behaviors of the fish shoals are difficult to effectively track. The continuous endurance time is short, the existing underwater robot depends on limited battery electric quantity, the continuous endurance time is short, the long-time monitoring requirement cannot be met, and particularly the problem is particularly remarkable when continuous shoal state tracking is performed in remote sea areas.
Disclosure of Invention
The invention provides a multi-source data fusion-based high-anti-flow multi-point observation type fish swarm monitoring underwater robot, which can be kept stable under complex ocean current conditions, has high-efficiency image recognition capability and can accurately track fish swarms moving rapidly.
In order to solve the problems, the technical scheme provided by the invention is as follows:
The embodiment of the invention provides a multi-source data fusion-based high-flow-resistance multi-point observation type fish school monitoring underwater robot, which comprises a shell (1), wherein a self-adaptive ocean current resistance system (2) is arranged at the front end position of the top of the shell (1), a telescopic multi-sensor fusion system (3) is arranged at the front end position of the bottom of the shell (1), an energy system (4) is arranged on the shell (1), and 4 vector thrusters (201) are arranged around the shell (1);
The self-adaptive ocean current resistance system (2) comprises an ocean current information detection module and a PID control algorithm real-time regulation and control propeller module, wherein the ocean current information detection module is used for collecting ocean current information in real time, including water flow speed, direction and turbulence intensity;
The telescopic multi-sensor fusion system (3) comprises an environment monitoring and data acquisition module, a multi-source data fusion and overlapping processing module, a fish group identification and track prediction module, an information output module and an energy management module, wherein the telescopic multi-sensor fusion system (3) acquires multi-dimensional data of a fish group by combining a plurality of sensors and performs fusion analysis on the data by utilizing a deep learning algorithm, so that efficient fish group identification and tracking are realized.
According to an alternative embodiment of the invention, the environment monitoring and data acquisition module comprises sensor data acquisition and data preprocessing, wherein the data acquisition sensor comprises a high-resolution camera (301), an underwater sonar (302), an underwater illumination system (303) and an ocean current sensor (304), and the data preprocessing is used for denoising, resolution adjustment and data enhancement.
The multi-source data fusion and overlap processing module comprises a feature extraction technology, a sensor data fusion technology and an overlap elimination technology, wherein the feature extraction technology is used for extracting features of a fish-swarm image, such as edges and shape features, through a convolutional neural network CNN, the sensor data fusion is used for fusing multi-sensor data of optics and sonar to obtain complete fish-swarm information, the overlap elimination technology is used for classifying and tracking fish-swarm individuals through a deep learning algorithm by adopting deep learning processing including a convolutional layer, a pooling layer, a full-connection layer and a classifier Softmax.
According to an optional embodiment of the invention, the fish school identification and track prediction module comprises fish school individual identification and fish school track prediction and tracking, wherein the fish school individual identification classifies and tracks fish school individuals by using a deep learning algorithm, and the fish school track prediction and tracking predicts the movement track of the fish school based on historical data and a deep learning model.
According to an alternative embodiment of the invention, the energy management module utilizes solar energy, water flow power generation and intelligent energy scheduling to manage intelligent allocation of different energy sources, so that long-time operation is ensured.
In an alternative embodiment of the invention, the adaptive ocean current resistance system (2) comprises a water flow sensor, an attitude sensor and an acceleration sensor, and is used for monitoring the speed and the direction of water flow in real time.
In an alternative embodiment of the present invention, the PID control algorithm control equation is:
;
the self-adaptive ocean current resistance system (2) adjusts the power of the propeller through proportion, integration and differentiation, adjusts the gesture of the underwater robot in real time, wherein e (t) represents the error between the actual position and the expected position, the parameter adjusting range is that the value range of a proportional gain K p is 0.1-1.0 and used for controlling the response speed, the value range of an integral gain K i is 0.01-0.1 and used for eliminating steady-state errors, the value range of a differential gain K d is 0.01-0.1 and used for improving the disturbance rejection capability, and the application condition is that a PID control algorithm is suitable for a complex ocean current environment with the water flow speed changing range of 0.5-3.0 m/s, and the thrust output of the propeller is adjusted in real time so as to ensure that the underwater robot keeps gesture stable and navigation accuracy under the condition of ocean current abrupt change.
According to an alternative embodiment of the invention, the energy system (4) comprises a solar panel (401) and a water flow power generation device (402), wherein the solar panel (401) is arranged at the middle position of the top of the shell (1) and is used for capturing solar energy, the water flow power generation device (402) is arranged at the rear end position of the bottom of the shell (1), and the water flow power generation device (402) utilizes water flow to push a turbine to generate power so as to provide additional power support.
In an alternative embodiment of the present invention, the water flow power generation device (402) evaluates the power generation performance of the water flow turbine by using a water flow power generation efficiency formula: wherein ρ is the density of water, A is the frontal area of the turbine, and V is the water flow rate.
Compared with the prior art, the embodiment of the invention provides the high-anti-flow multi-point observation type fish school monitoring underwater robot based on multi-source data fusion, which has the following beneficial effects:
(1) The shoal monitoring underwater robot is specially used for shoal monitoring and tracking tasks, can be kept stable in complex water flow through a vector propeller self-adaptive ocean current resistance system and a multi-sensor fusion technology, and meanwhile, the shoal identification is carried out by adopting the cluster underwater robot based on a deep learning algorithm, so that the accuracy and efficiency of fish tracking are greatly improved. In addition, the integrated ocean current-solar energy system enables the underwater robot to have long-time endurance, and is suitable for long-distance and long-time operation requirements.
(2) The combination of the vector propeller and the ocean current detection sensor enables the underwater robot to sense the ocean current change in real time, and the propulsion and the direction are adjusted through a PID control algorithm, so that the stability of the underwater robot is maintained. The stable control system ensures that the efficient fish swarm tracking and data acquisition work can be still performed in an environment with severe ocean current variation. The method has the direct effects that by introducing the self-adaptive ocean current resistance system, the underwater robot can adjust the output and the direction of the vector propeller in real time, so that the vector propeller can keep high stability under complex open ocean current conditions, the out-of-control phenomenon caused by water current fluctuation is obviously reduced, continuous monitoring is ensured, the fish swarm tracking in strong ocean current and deep sea environments is possible, the availability of ROV is obviously improved, the method is suitable for wider ocean conditions, and the application range is expanded.
(3) The method has the advantages that the fish shoal is efficiently identified and tracked, and the adopted cluster type multi-angle shooting and deep learning model can extract the fish body characteristics to accurately identify under the condition that fishes are overlapped and fast swimming through training a large number of fish pictures. Meanwhile, the accuracy of identification is further improved by fusing the data of the acoustic sensor and the optical sensor. The method has the advantages that the accuracy of identifying and tracking the individual fish shoal is greatly improved based on the fish shoal identification technology of deep learning and multi-sensor fusion, and even under the conditions of overlapping and high-speed swimming of the fish shoal, the individual fish can be effectively distinguished and accurate data can be provided. The method has the technical effects that the improvement reduces the recognition errors caused by overlapping or rapid movement in the traditional image recognition, enhances the operation efficiency of the underwater robot in the complex fish shoal state, and improves the scientificity and accuracy of fish shoal monitoring and research.
(4) The energy recovery and endurance are improved, the water flow power generation device drives the turbine to generate power through water flow energy, and the solar panel absorbs light energy during water surface operation, so that the two energy recovery modes are combined to ensure that the equipment keeps power supply during long-time operation, and endurance time is greatly prolonged. The underwater robot has the advantages that the underwater robot greatly prolongs the endurance time by integrating the water flow power generation and solar energy technology, and can work for a long time without frequent replacement of batteries or charging, so that the underwater robot is suitable for continuous monitoring requirements. Compared with the traditional battery-powered underwater robot, the device has the advantages that the sustainable operation capability of the device is improved, long-term monitoring of remote areas such as open sea, deep sea and the like is possible, the design not only improves the environmental friendliness, but also reduces the operation and maintenance cost, and the device has wide market prospect and competitive advantage in the fields such as marine ecological protection, resource exploration and the like.
Drawings
In order to more clearly illustrate the embodiments or the technical solutions in the prior art, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a high anti-flow multi-point observation type fish school monitoring underwater robot based on multi-source data fusion according to an embodiment of the present application.
Fig. 2 is a schematic diagram of a bottom structure of a high anti-flow multi-point observation type fish-shoal monitoring underwater robot based on multi-source data fusion according to an embodiment of the present application.
Fig. 3 is a front view of a high anti-flow multi-point observation type fish school monitoring underwater robot based on multi-source data fusion according to an embodiment of the present application.
Fig. 4 is a schematic diagram of a self-adaptive ocean current resistance system and a telescopic multi-sensor fusion system of a high-current-resistance multi-point observation type fish school monitoring underwater robot based on multi-source data fusion.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
As shown in fig. 1, the embodiment of the invention provides a multi-source data fusion-based high-flow-resistance multi-point observation type fish school monitoring underwater robot, which comprises a shell 1, wherein an adaptive ocean current resistance system 2 is arranged at the front end position of the top of the shell 1, a telescopic multi-sensor fusion system 3 is arranged at the front end position of the bottom of the shell 1, an energy system 4 is arranged on the shell 1, and 4 vector thrusters 201 are arranged around the shell 1.
The adaptive ocean current resistance system 2 as in fig. 2 includes a water flow sensor, an attitude sensor and an acceleration sensor for monitoring the water flow speed and direction in real time. The sensors for collecting data of the telescopic multi-sensor fusion system 3 shown in fig. 3 comprise a high-resolution camera 301, an underwater sonar 302, an underwater illumination system 303 and a ocean current sensor 304, fish are identified in real time through a model trained by a deep learning algorithm, and sensor data are fused with visual information to improve identification accuracy.
As shown in FIG. 4, the adaptive ocean current resistance system 2 comprises an ocean current information detection module and a PID control algorithm real-time regulation and control propeller module, wherein the ocean current information detection module is used for acquiring ocean current information in real time, including water flow speed, direction and turbulence intensity. The control algorithm regulates and controls the power and the direction of the vector propeller 201 in real time by utilizing the PID control algorithm according to the ocean current change, so that the stability of the underwater robot in complex ocean currents is ensured.
The PID control algorithm control equation is:
;
The self-adaptive ocean current resistance system (2) adjusts the power of the propeller through proportion, integration and differentiation, adjusts the gesture of the underwater robot in real time, wherein e (t) represents the error between the actual position and the expected position, the parameter adjusting range is that the value range of a proportional gain K p is 0.1-1.0 and used for controlling the response speed, the value range of an integral gain K i is 0.01-0.1 and used for eliminating steady-state errors, the value range of a differential gain K d is 0.01-0.1 and used for improving the anti-disturbance capability, and the application condition is that a PID control algorithm is suitable for a complex ocean current environment with the water current speed changing range of 0.5-3.0 m/s, and the thrust output of the propeller is adjusted in real time, so that the gesture stability and the navigation precision of the underwater robot under the ocean current abrupt change condition are ensured.
As shown in fig. 4. The telescopic multi-sensor fusion system 3 comprises an environment monitoring and data acquisition module, a multi-source data fusion and overlapping processing module, a fish school identification and track prediction module, an information output module and an energy management module. The environment monitoring and data acquisition module comprises sensor data acquisition and data preprocessing, and the data acquisition sensor comprises a high-resolution camera 301, an underwater sonar 302, an underwater illumination system 303 and an ocean current sensor 304. The data preprocessing is used for denoising, resolution adjustment and data enhancement processing.
The multi-source data fusion and overlap processing module comprises feature extraction, sensor data fusion and overlap elimination technology, wherein the feature extraction is used for extracting the features of the fish swarm image, such as edge and shape features, through a convolutional neural network CNN. The sensor data fusion fuses optical and sonar multi-sensor data to obtain complete fish swarm information, the overlap elimination technology adopts deep learning processing including a convolution layer, a pooling layer, a full connection layer and a classifier Softmax, and a deep learning algorithm is used for classifying and tracking fish swarm individuals.
The fish swarm identification and track prediction module comprises fish swarm individual identification and fish swarm track prediction and tracking, wherein the fish swarm individual identification classifies and tracks fish swarm individuals by using a deep learning algorithm, and the fish swarm track prediction and tracking predicts the motion track of the fish swarm based on historical data and a deep learning model. The energy system utilizes solar energy, water flow power generation and intelligent energy scheduling to manage intelligent allocation of different energy sources, so that long-time operation is ensured.
The energy system 4 includes a solar panel 401 and a water current power generation device 402, the solar panel 401 being disposed at a top intermediate position of the housing 1 for capturing solar energy. The water flow power generation device 402 is arranged at the bottom rear end position of the shell 1, and the water flow power generation device 402 utilizes water flow to push the turbine to generate power, so that additional power support is provided.
The water flow power generation device 402 evaluates the power generation performance of the water flow turbine by a water flow power generation efficiency formula:
wherein ρ is the density of water, A is the frontal area of the turbine, and V is the water flow rate.
In the above way, the shoal of fish monitoring underwater robot provided by the invention is provided with a stability optimization system. By adopting advanced hydrodynamic design and intelligent control algorithm, the underwater robot disclosed by the invention can adapt to external environment changes in real time and maintain the stability of the underwater robot. In particular, an underwater robot ROV is equipped with a plurality of vector thrusters capable of automatically adjusting the direction and speed of propulsion in accordance with real-time monitored water flow conditions. The technology allows the ROV of the underwater robot to maintain high stability in a complex ocean current environment, and effectively avoids the problem that the existing equipment is easy to be disturbed by water current and lose control.
The specific measures are that water flow information (speed, direction, turbulence intensity and the like) is acquired in real time through a plurality of ocean current sensors. The self-adaptive ocean current resistance system uses a PID control algorithm to automatically adjust the vector direction and the thrust of the propeller, so that the ROV of the underwater robot is ensured to be stable in water. The response time of the whole adjustment process is short, and the underwater robot ROV can quickly react in a complex ocean current environment. Compared with the traditional propeller system, the vector propeller can carry out accurate thrust adjustment according to the real-time hydrodynamic characteristics, and the stability and adaptability of the ROV of the underwater robot in complex water flow are greatly improved.
The fish school monitoring underwater robot has an efficient image recognition function. By adopting the telescopic multi-sensor fusion system 3 technology (acoustic and optical), the precise tracking of fish individuals is realized by cooperatively shooting in a cluster mode from multiple angles of the ROV of the underwater robot and combining magnetic force and acoustic signals for auxiliary identification. The robot integrates a deep learning algorithm, particularly a convolutional neural network CNN, and combines data information acquired by a plurality of sensors, so that the robot can accurately identify a target in fish which moves rapidly. By training the model, the system can identify different kinds of fishes and characteristics thereof, and can ensure the accuracy and rapidity of identification even under the condition that fish shoals overlap. The method specifically comprises the steps that a plurality of underwater robots capture multi-angle images of the fish shoals in real time through optical cameras, and meanwhile, distance and space distribution information of the fish shoals are obtained through sonar. And splicing multiple images through a deep learning model (such as CNN), and extracting the characteristics of the fish by combining sensor data to solve the problem of fish overlapping. And the multisensor fuses data analysis, and provides additional physical information by utilizing acoustic and magnetic signals, so that the accuracy of fish identification is further improved. The fish shoal identification method has the innovation points that the accuracy of fish shoal identification is remarkably improved through the combination of multi-angle collaborative shooting and multi-source physical signals, and the identification difficulty caused by fish overlapping is solved.
The fish school monitoring underwater robot provided by the invention has the advantage of enhancing the endurance. The invention designs a high-efficiency energy system, which combines solar energy and water flow power generation technology to enhance the cruising ability of an underwater robot. The solar panel can collect energy on the water surface, and the water flow generator utilizes the water flow kinetic energy to perform power conversion, so that the robot is not easy to consume power during long-time operation. The innovation obviously prolongs the endurance capacity of the equipment, so that the equipment can be monitored in an open sea area for a long time and continuously, and the defect of short endurance time of the traditional robot is overcome. The method comprises the specific steps of installing a miniature water flow generator below the ROV of the underwater robot, and charging a battery by capturing the kinetic energy of water flow. And covering the surface of the ROV of the underwater robot with a solar panel, and charging by utilizing solar energy when the ROV floats to the water surface. The energy system intelligently allocates two energy sources for use, so that the ROV of the underwater robot can be ensured to continue to travel for a long time. The system prolongs the duration of the ROV of the underwater robot through natural energy recovery, and is suitable for long-term monitoring tasks in open sea.
In a complex open sea environment, ocean currents can generate strong water flow interference, so that the ROV of the underwater robot is difficult to keep running stably. Most existing underwater robots rely on fixed propulsion systems, are difficult to adapt quickly in the face of changing currents, and are prone to run away or drift. The invention adopts a self-adaptive ocean current resistance system, and monitors the speed, direction and strength of external water flow in real time by integrating a multi-direction propeller, an accelerometer, an ocean current sensor and other devices on an ROV of an underwater robot. When the system detects the water flow change, a control algorithm is automatically started, and the ROV of the underwater robot automatically adjusts the posture by adjusting the power and the direction of each propeller, so that the ROV of the underwater robot is ensured to be kept stable in water. The method comprises the specific steps of 1, collecting water flow information in real time through a plurality of ocean current sensors, wherein the water flow information comprises water flow speed, direction, turbulence intensity and the like. 2. A control algorithm (such as an adaptive algorithm based on PID control) built in the system calculates the working parameters required by each propeller in real time according to the sensor data. 3. And each propeller adjusts the working state according to the calculation result, and adjusts the thrust direction and the thrust magnitude, so that the influence of external water flow is resisted, and the stability of the ROV of the underwater robot is ensured. 4. The response time of the whole adjusting process is short (in millisecond level), sudden water flow change can be dealt with in real time, and the ROV of the underwater robot can safely work in a complex ocean current environment. The system has the advantages that the system ensures that the underwater robot ROV can keep stable posture in a complex water flow environment, prevents equipment from being out of control or deviating from a set track caused by ocean current change, and ensures that the underwater robot ROV can continuously carry out fish swarm tracking and shooting tasks.
In the multi-sensor fusion deep learning fish school recognition system, under the condition that fish schools are dense and fish swimming speed is high, the traditional visual recognition system often cannot accurately distinguish individual fish due to overlapping and rapid movement of fish, so that recognition accuracy is reduced. The invention designs a multi-sensor fusion deep learning recognition system, which is used for collecting multi-dimensional data of a fish shoal by combining a plurality of sensors (such as an optical camera and sonar equipment) and carrying out fusion analysis on the data by utilizing a deep learning algorithm so as to realize efficient fish shoal recognition and tracking. The invention provides a multi-sensor fusion deep learning fish school recognition system, which combines multi-dimensional data of fish schools collected by a plurality of sensors (such as optical cameras and sonar equipment) and by utilizing a deep learning algorithm to perform data fusion analysis, realizes efficient recognition and tracking of fish schools. Capturing at multiple angles, namely capturing images of the fish shoal in real time by adopting a high-resolution optical camera, and acquiring distance and distribution information of the fish shoal by combining sonar equipment. (2) Feature extraction and fusion, namely fusion of multiple sensors acquired (3) through a Convolutional Neural Network (CNN), wherein the deep learning algorithm can automatically learn the features of fish through training of a large amount of fish image data, and is suitable for fish shoal tracking scenes of different types and forms. (4) The space cooperation is that a plurality of underwater robots are used for cooperation shooting, and the multi-image splicing is combined, so that the fish school individuals can be identified efficiently from a plurality of angles, and meanwhile, the fish school identification accuracy expected effect is further improved by means of magnetic or acoustic signal auxiliary identification. The system solves the recognition problem of the traditional visual recognition system under the conditions of fish shoal overlapping and fish rapid swimming, obviously improves the accuracy and efficiency of fish shoal tracking, and ensures that the ROV can complete the monitoring task in a complex fish shoal environment.
The energy recovery type continuous voyage system is characterized in that the battery capacity of the existing underwater robot ROV is limited, and the battery needs to be frequently replaced or returned to be charged when a task is monitored for a long time, so that the continuous operation efficiency is influenced, especially in remote areas such as open sea. The invention introduces an energy recovery type cruising system, combines water flow power generation and solar energy technology, and provides continuous energy supply for the ROV of the underwater robot by capturing external natural energy (such as ocean water flow kinetic energy and solar light energy), thereby reducing the dependence on batteries. The method comprises the specific steps of generating electricity by using flow energy, namely installing a miniature turbine generator below or at the tail of the underwater robot ROV, and when the underwater robot ROV moves in water or encounters water flow, the water flow pushes the turbine to rotate to generate electricity so as to directly charge a battery or provide power for a propulsion system. Solar charging, namely covering the surface of the underwater robot ROV with a high-efficiency solar panel, and charging by utilizing sunlight when the underwater robot ROV floats to the water surface. The system works cooperatively with the water flow power generation system to ensure that additional power support can be obtained in different scenes. The intelligent energy management energy system enables the power reserve to be always kept at the optimal level through intelligent allocation of the two energy sources. The energy recovery type continuous voyage system has the advantages that the continuous voyage time of the ROV of the underwater robot is remarkably prolonged, the energy recovery type continuous voyage system is particularly suitable for open sea or long-time monitoring tasks, and the bottleneck problem of insufficient continuous voyage capability of the existing ROV of the underwater robot is solved.
The following classical algorithms are adopted in the invention to realize the key functions of the ROV of the underwater robot for monitoring the fish shoal:
(1) Convolutional Neural Networks (CNNs) are used for fish-shoal identification, in which we perform feature extraction on fish-shoal images through convolutional operations. The convolutional neural network convolves the input image f with a convolution kernel by the following formula: the formula is used for extracting the characteristics of edges, shapes and the like of the image and helping to identify fast swimming and overlapping fish shoals. (2) The PID control algorithm is used for propeller adjustment, and the propeller adjustment is based on the PID control algorithm and is used for maintaining the stability of the ROV under water. The control equation is: Wherein e (t) represents the error between the actual position and the desired position, the system adjusts the power of the propeller by proportional, integral and derivative, and adjusts the attitude of the ROV in real time. (3) Energy recovery efficiency of a water flow power generation system in which we use a water flow power generation efficiency formula to evaluate the power generation performance of a water flow turbine: . Wherein ρ is the density of water, A is the frontal area of the turbine, and V is the water flow rate. The formula is used for analyzing the efficiency of the power generation system under different water flow conditions and ensuring that the cruising ability meets the long-time monitoring requirement.
The high-anti-flow multi-point observation type fish school monitoring underwater robot based on multi-source data fusion has the following innovation points:
The innovation point 1 is that the intelligent sensing of the underwater environment and the pre-judging technology of the underwater target object movement are based on multi-source data fusion. The invention provides an underwater environment intelligent sensing technology based on a multi-source data fusion and deep learning model, which combines data input of various sensors such as optics, acoustics and the like, and solves recognition challenges which are difficult to overcome by traditional technologies such as individual fish shoal overlapping, rapid swimming, complex ocean current interference and the like. The technology can accurately identify and track the dynamic position of the fish school individuals in real time in a complex water area environment, and has high robustness and self-adaption capability. According to the technical scheme 1, the multi-source data fusion and high-precision identification are realized by the system through multi-angle synchronous shooting, the high-resolution cameras and the acoustic sensors which are equipped by a plurality of underwater robots are adopted to shoot fish shoals in real time and acquire data from different directions, and the image data of the different sensors are spliced into a complete three-dimensional image of the fish shoals, so that the difficulty in identification caused by fish overlapping is solved. In the image stitching process, the overlapped individuals are further separated by utilizing acoustic and visual data, so that the identification and tracking of the fish school individuals are more accurate. The acoustic sensor further provides spatial depth and distance information on the basis of providing visual information. The data of various sensors are integrated in real time through a data fusion algorithm to form rich three-dimensional images and position information, so that high recognition precision and efficiency are maintained under the condition that fish swarm individuals overlap.
And the real-time prediction and the motion prediction are performed by combining visual and acoustic information by the system, and performing real-time prediction on the swimming direction and speed change of the fish shoal by using a deep learning model. And (3) adopting a PID control algorithm to infer a motion track in a short time in the future based on the current shoal position and speed data. The multi-parameter optimization process monitors the speed, distance and direction change of fish in real time, and forms a reliable motion prejudging mechanism. Optimizing the target tracking prediction model, namely constructing a mapping relation of the distance between the underwater robot and the target fish swarm individual, the target object speed and the speed change thereof by combining hydrodynamic motion characteristics (such as turning, acceleration, deceleration characteristics and the like) of the underwater robot, so as to refine the accuracy of the target tracking prediction model. The model integrates the six-degree-of-freedom motion parameters of the underwater robot, realizes continuous tracking and shooting of the fish swarm target, ensures complete data acquisition of fish swarm behaviors, and can keep a stable tracking effect even under the condition of ocean current mutation.
Innovation point 2 is a high-mobility underwater traveling technology based on full-rotation vector propulsion. The invention provides an underwater traveling technology based on a full-rotation vector propeller and real-time ocean current detection, which enables an underwater robot to adaptively adjust the propelling direction and the thrust in a complex water flow environment through the cooperative work of multi-directional vector propulsion and an ocean current sensor, and keeps a highly stable traveling effect. The system combines hydrodynamic optimization and PID control algorithm, accurately responds to water flow change, realizes high maneuverability and accurate positioning in turbulent environment, and provides technical support for long-time ocean monitoring and fish swarm tracking tasks. The technical scheme 2 is that the propeller arrangement scheme and the working mechanism are that the underwater robot is provided with four full-rotation vector propellers which are respectively arranged at four corners of the robot and symmetrically distributed so as to ensure balanced thrust and maneuverability. Each propeller can rotate 360 degrees on a vertical shaft, and the thrust force can be independently adjusted. Through the cooperation of the propeller and the ocean current sensor, when the sensor detects lateral water flow, the propeller positioned on the side face automatically increases reverse thrust to balance the influence caused by external water flow, and the propellers in other directions are adjusted as required to maintain the integral propulsion effect. For example, when the underwater robot travels forward and encounters lateral water flow, the system can enable the side thrusters to apply thrust in the opposite direction, and the rear side thrusters increase the thrust according to the current path, so that the influence of the lateral water flow is effectively counteracted. The blades and the motor of the propeller are optimally designed according to hydrodynamic characteristics, the thrust is stable, the drag force is small, and the underwater robot is not easy to deviate from the direction in the propelling process.
Hydrodynamic characteristics and propeller response optimization to ensure stability under high ocean currents, the propeller is designed with high efficiency propeller and is equipped with a high-precision motor control module. The design can quickly respond in the environment with abrupt change of flow velocity, and the hydrodynamic balance is accurately controlled by changing the angle and the thrust of the propeller. The system adopts a PID control algorithm to input real-time ocean current data into a control module, realizes dynamic response optimization of the propeller through proportion, integral and differential adjustment, ensures that the propeller adjusts water flow change in millisecond-level time, and therefore maintains the stability of the underwater robot. The self-adaptive adjusting system is specifically realized in that a self-adaptive adjusting algorithm arranged in the system receives real-time data of the ocean current sensor and compares the real-time data with target path parameters of the underwater robot. If the sensor detects a change in water flow exceeding a preset threshold (e.g., a water flow rate exceeding 1 meter per second or a flow direction deviation exceeding 15 degrees), the control module immediately adjusts the angle and thrust of the corresponding propeller to counteract the effects of external water flow. For example, when reverse flow is detected in the front, the rear propeller will rapidly increase the thrust, while the front propeller relatively decreases the thrust, thereby maintaining the forward speed of the underwater robot. The self-adaptive adjusting system can stably control the speed and the direction of the underwater robot in a strong ocean current environment, and ensure accurate positioning and stable operation of the underwater robot in a complex water area. The full-rotation vector propulsion technology can realize extremely high flexibility and stability, and is suitable for the scenes such as ocean shoal monitoring, deep sea scientific research, submarine topography exploration and the like. Compared with the traditional propulsion system, the design has the quick response and disturbance rejection capability to ocean currents, and the stability and the endurance time of the underwater robot in a long-time monitoring task are prolonged. In actual operation, the real-time cooperative work of the propeller and the ocean current sensor obviously reduces the operation difficulty caused by external environment change, ensures the stable operation of the underwater robot in a complex water area, and improves the consistency and precision of data acquisition.
Innovation point 3 is a long-endurance operation technology based on combination of an energy capturing technology and a chemical battery technology. The invention provides a hybrid clean energy supply system combining fluid energy power generation, solar power generation and sea water batteries, which provides high-efficiency long-endurance capacity for an underwater robot. The system greatly prolongs the working time of the underwater robot and reduces the requirement of frequently replacing batteries by the combined application of the energy capturing and energy storage technology. The scheme is particularly suitable for long-time monitoring tasks of open sea and complex water areas, and ensures that the underwater robot stably operates for a long time. According to the technical scheme 3, the system designs a set of flow energy power generation device by using a flow energy power generation and propeller cooperative working mechanism, and a miniature water flow turbine is arranged at the bottom or the side surface of the underwater robot, so that the turbine is driven to rotate by water flow to generate power. The device not only can provide continuous power for the underwater robot, but also can assist the operation of the propeller when necessary. When the water flow speed is suitable for power generation, the rotation of the turbine generates power to charge the battery or directly supply power to the propulsion system, and when the propulsion demand is large, the system can switch the flow energy power generation mode, so that the kinetic energy of the turbine directly assists the propeller to work, thereby saving the energy consumption of the battery. The dual-mode cooperative work mechanism not only realizes the capture of flow energy, but also can efficiently utilize external kinetic energy to assist in propulsion, and effectively improves the endurance and efficiency of the system. The solar energy capturing system and the power management are that the surface of the underwater robot is provided with a high-efficiency solar panel, and when the underwater robot floats to the water surface, the solar panel can rapidly capture solar energy, convert the solar energy into electric energy and store the electric energy in a battery. Through intelligent allocation of the energy system, the system can reasonably allocate solar energy to be used according to task demands and ambient lighting conditions so as to supply power for basic functions such as a control system and a sensor module preferentially, and consumption of a battery is reduced, so that endurance time is prolonged. In addition, under the condition of sufficient sunlight, solar energy can charge a battery, so that the independent operation time of the underwater robot is further prolonged.
The seawater battery technology and the application of the reverse chemical process are that the system also integrates a chemical battery based on seawater electrolyte, and provides additional clean energy for the underwater robot. Seawater batteries use seawater as an electrolyte to generate electricity through a reverse chemical reaction. Specifically, the seawater battery realizes a process of converting chemical energy into electric energy by performing reduction and oxidation reactions on ions in seawater, thereby providing stable power supply. Such reverse chemistry not only provides power directly to the robot, but also provides backup power to the system during emergency situations or long-term operation. Compared with the traditional battery, the seawater battery has longer service life and good environmental protection, does not need frequent electrolyte replacement, and is particularly suitable for long-term underwater operation requirements. And the intelligent energy management module in the system can dynamically allocate according to the current power requirement and the states of different energy sources. And the power distribution and switching are performed among the flowing energy, the solar energy and the seawater battery, so that the underwater robot can keep optimal power reserve at any time. The intelligent management module can automatically detect the current battery electric quantity and the output state of each energy system, and when the electric quantity is insufficient, the intelligent management module preferentially starts the seawater battery or the energy-flowing power generation to supplement the required electric power, and preferentially utilizes solar power generation in an environment with sufficient illumination so as to keep the electric quantity sufficient state of the main battery, thereby greatly reducing the consumption frequency of the battery and improving the endurance stability of the equipment.
In summary, although the present invention has been described in terms of the preferred embodiments, the above-mentioned embodiments are not intended to limit the invention, and those skilled in the art can make various modifications and alterations without departing from the spirit and scope of the invention, so that the scope of the invention is defined by the appended claims.
Claims (6)
1. The high-current-resistance multi-point observation type fish monitoring underwater robot based on multi-source data fusion is characterized by comprising a shell (1), wherein a self-adaptive ocean current resistance system (2) is arranged at the front end position of the top of the shell (1), a telescopic multi-sensor fusion system (3) is arranged at the front end position of the bottom of the shell (1), an energy system (4) is arranged on the shell (1), and 4 vector thrusters (201) are arranged around the shell (1);
The self-adaptive ocean current resistance system (2) comprises an ocean current information detection module and a PID control algorithm real-time regulation and control propeller module, wherein the ocean current information detection module is used for collecting ocean current information in real time, including water flow speed, direction and turbulence intensity;
The telescopic multi-sensor fusion system (3) comprises an environment monitoring and data acquisition module, a multi-source data fusion and overlapping processing module, a fish group identification and track prediction module, an information output module and an energy management module, wherein the telescopic multi-sensor fusion system (3) acquires multi-dimensional data of a fish group by combining a plurality of sensors and performs fusion analysis on the data by utilizing a deep learning algorithm, so that efficient fish group identification and tracking are realized;
The environment monitoring and data acquisition module comprises sensor data acquisition and data preprocessing, wherein the data acquisition sensor comprises a high-resolution camera (301), an underwater sonar (302), an underwater illumination system (303) and an ocean current sensor (304), and the data preprocessing is used for denoising, resolution adjustment and data enhancement;
The multi-source data fusion and overlap processing module comprises a feature extraction technology, a sensor data fusion technology and an overlap elimination technology, wherein the feature extraction technology is used for extracting the features of a fish-swarm image, such as edges and shape features, through a convolutional neural network CNN;
the fish school identification and track prediction module comprises fish school individual identification and fish school track prediction and tracking, wherein the fish school individual identification classifies and tracks fish school individuals by using a deep learning algorithm, and the fish school track prediction and tracking predicts the movement track of the fish school based on historical data and a deep learning model.
2. The multi-source data fusion-based high-flow-resistance multi-point observation type fish monitoring underwater robot is characterized in that the energy management module manages intelligent allocation of different energy sources by utilizing solar energy, water flow power generation and intelligent energy scheduling, and long-time operation is ensured.
3. The multi-source data fusion-based high-current-resistance multi-point observation type fish monitoring underwater robot according to claim 1, wherein the self-adaptive ocean current resistance system (2) comprises a water current sensor, an attitude sensor and an acceleration sensor, and is used for monitoring the water current speed and direction in real time.
4. The multi-source data fusion-based high-flow-resistance multi-point observation type fish monitoring underwater robot of claim 1, wherein the control equation of the PID control algorithm is as follows:
;
the self-adaptive ocean current resistance system (2) adjusts the power of the propeller through proportion, integration and differentiation, adjusts the gesture of the underwater robot in real time, wherein e (t) represents the error between the actual position and the expected position, the parameter adjusting range is that the value range of a proportional gain K p is 0.1-1.0 and used for controlling the response speed, the value range of an integral gain K i is 0.01-0.1 and used for eliminating steady-state errors, the value range of a differential gain K d is 0.01-0.1 and used for improving the disturbance rejection capability, and the application condition is that a PID control algorithm is suitable for a complex ocean current environment with the water flow speed changing range of 0.5-3.0 m/s, and the thrust output of the propeller is adjusted in real time so as to ensure that the underwater robot keeps gesture stable and navigation accuracy under the condition of ocean current abrupt change.
5. The multi-source data fusion-based high-flow-resistance multi-point observation type fish monitoring underwater robot is characterized in that the energy system (4) comprises a solar panel (401) and a water flow power generation device (402), the solar panel (401) is arranged at the middle position of the top of the shell (1) and used for capturing solar energy, the water flow power generation device (402) is arranged at the rear end position of the bottom of the shell (1), and the water flow power generation device (402) utilizes water flow to push a turbine to generate power so as to provide additional power support.
6. The multi-source data fusion-based high-flow-resistance multi-point observation fish monitoring underwater robot of claim 5, wherein the water flow power generation device (402) evaluates the power generation performance of a water flow turbine by a water flow power generation efficiency formula: wherein ρ is the density of water, A is the frontal area of the turbine, and V is the water flow rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411658721.1A CN119142491B (en) | 2024-11-20 | 2024-11-20 | A highly flow-resistant multi-point observation fish school monitoring underwater robot based on multi-source data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411658721.1A CN119142491B (en) | 2024-11-20 | 2024-11-20 | A highly flow-resistant multi-point observation fish school monitoring underwater robot based on multi-source data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119142491A true CN119142491A (en) | 2024-12-17 |
| CN119142491B CN119142491B (en) | 2025-01-28 |
Family
ID=93804203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411658721.1A Active CN119142491B (en) | 2024-11-20 | 2024-11-20 | A highly flow-resistant multi-point observation fish school monitoring underwater robot based on multi-source data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119142491B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119984407A (en) * | 2025-04-14 | 2025-05-13 | 广东海洋大学 | A multi-parameter in-situ detection data analysis system for marine ranching |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007127271A2 (en) * | 2006-04-24 | 2007-11-08 | Farsounder, Inc. | 3-d sonar system |
| US20110291862A1 (en) * | 2010-05-28 | 2011-12-01 | Conocophillips Company | Ice data collection system |
| WO2017140096A1 (en) * | 2016-02-18 | 2017-08-24 | 北京臻迪科技股份有限公司 | Unmanned ship and system |
| CN112644646A (en) * | 2020-11-24 | 2021-04-13 | 浙江理工大学 | Underwater robot intelligent system for large-water-area fish resource investigation and working method |
| WO2023197781A1 (en) * | 2022-04-12 | 2023-10-19 | 株洲中车时代电气股份有限公司 | Autonomous underwater exploration system and method, method for automatically launching auv, and method for automatically recovering auv |
-
2024
- 2024-11-20 CN CN202411658721.1A patent/CN119142491B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007127271A2 (en) * | 2006-04-24 | 2007-11-08 | Farsounder, Inc. | 3-d sonar system |
| US20110291862A1 (en) * | 2010-05-28 | 2011-12-01 | Conocophillips Company | Ice data collection system |
| WO2017140096A1 (en) * | 2016-02-18 | 2017-08-24 | 北京臻迪科技股份有限公司 | Unmanned ship and system |
| CN112644646A (en) * | 2020-11-24 | 2021-04-13 | 浙江理工大学 | Underwater robot intelligent system for large-water-area fish resource investigation and working method |
| WO2023197781A1 (en) * | 2022-04-12 | 2023-10-19 | 株洲中车时代电气股份有限公司 | Autonomous underwater exploration system and method, method for automatically launching auv, and method for automatically recovering auv |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119984407A (en) * | 2025-04-14 | 2025-05-13 | 广东海洋大学 | A multi-parameter in-situ detection data analysis system for marine ranching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119142491B (en) | 2025-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Development and control of underwater gliding robots: A review | |
| CN119142491B (en) | A highly flow-resistant multi-point observation fish school monitoring underwater robot based on multi-source data fusion | |
| CN107608347B (en) | Distributed control unmanned ship cluster enclosure tracking method | |
| KR101313546B1 (en) | Camera robot of buoy type | |
| Dong et al. | Development of a whale-shark-inspired gliding robotic fish with high maneuverability | |
| KR101313545B1 (en) | Self power generating robot of buoy type | |
| CN108860454B (en) | An all-weather long-range unmanned sailboat design method | |
| CN108408009A (en) | A kind of intelligent submarine navigation device based on Raspberry Pi Raspberry Pi controllers | |
| KR101313306B1 (en) | Buoy type robot for monitoring conditions | |
| CN112960078B (en) | Unmanned sailing boat automatic driving system and method thereof | |
| CN107878669B (en) | The wisdom water surface monitors trimaran | |
| CN112214023A (en) | Real-time optimization method and navigation method of course of wave-propelled natural energy driven unmanned ship | |
| CN114771787B (en) | A control system, control method and vector angle selection method for an underwater robot vector thruster | |
| CN107730539B (en) | Autonomous underwater robot control system and sonar target tracking method | |
| CN208855818U (en) | A self-righting long-endurance seawater sampling wave energy solar catamaran unmanned ship | |
| CN106956751A (en) | The flying wing type sea aerodone system and implementation of powered by wave energy | |
| CN216374952U (en) | Intelligent underwater robot | |
| Yang et al. | Design of small monitoring rov for aquaculture | |
| CN212332938U (en) | An autonomous line patrol underwater helicopter for diversion tunnel detection | |
| CN113879494A (en) | Intelligent underwater robot and motion control method thereof | |
| CN113050665A (en) | Energy-saving underwater robot detection method and system based on SLAM framework | |
| Hu et al. | Underwater target following with a vision-based autonomous robotic fish | |
| Zhang et al. | Research on path following control system of wave gliders based on maneuverability demand estimator | |
| Ziegler et al. | Sensory feedback of a fish robot with tunable elastic tail fin | |
| CN119408657A (en) | Unmanned salvage vessel for surface micro-foreign object image recognition and image capture and processing method 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |