An intelligent robot fish-herding device with path planning and underwater terrain recognition

Abstract

The present invention relates to an intelligent robot fish-herding device with path planning and underwater terrain recognition, which is composed of an electric grid, an underwater robot and a remote control module. The electric grid includes a surface end and an underwater end, which are connected by a soft steel wire rope. The surface end is equipped with a generator, a high-voltage pulse device and a main control module; the underwater end is composed of multiple underwater robots, each of which is equipped with an angle sensor, a depth sensor, a GPS module and an infrared camera. The main control module receives and processes information from the surface camera and the underwater robot, analyzes the underwater environment using the mmsegmentation semantic segmentation algorithm, and sends the results to the remote control module. The remote control module is responsible for receiving images and path information, realizing status monitoring and manual path setting functions. This device integrates functions such as path planning and underwater terrain recognition, aiming to improve the efficiency and intelligence level of fish-herding operations.

Description

Technical Field

[0001] The invention belongs to the technical field of intelligent fish herding, and relates to an intelligent robot fish herding device with path planning and underwater terrain recognition. Background Art

[0002] Currently, both traditional fish-herding methods and existing electric fences suffer from relatively low efficiency and limited intelligence. As a crucial fishing tool, improving the efficiency and technological advancement of electric fences is crucial for reducing fishery production costs and improving productivity.

[0003] Existing electric fence fish-herding devices use a motor-driven system to pull a floating boat and electric fence to carry out the fish-herding operation. However, these devices are bulky, inflexible, and unable to control the intensity and frequency of the electric pulses. This not only consumes electricity but is also prone to damage. Furthermore, workers cannot monitor the operation of the fish-herding device and manually intervene based on actual conditions, resulting in a low level of automation. Furthermore, actual fishing scenarios are quite diverse. For example, the surrounding and underwater environments of reservoirs are complex, and may be located in forests or mountainous areas. The electric fence is easily entangled by underwater foreign objects such as branches, which can damage and render the device useless. Summary of the Invention

[0004] In view of this, the object of the present invention is to provide an intelligent robot fish-herding device with path planning and underwater terrain recognition.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent robot fish-herding device with path planning and underwater terrain recognition includes an electric fence, the electric fence comprising a surface end that floats on the water surface and an underwater end that connects to multiple underwater robots for underwater travel; the surface end and the underwater end are connected by multiple rows of soft steel wire ropes; the surface end is equipped with a generator, a high-voltage pulse device, a main control module, a surface camera, and left and right thrusters; the underwater robots at the underwater end include a robot body, an angle sensor, a depth sensor, a GPS module, and an infrared camera; and also includes a remote control module;

[0007] The generator is used to supply power to each device module; the high-voltage pulse equipment is used to apply high-voltage pulse current to the soft steel wire rope; the surface camera is used to collect surface images; the robot body is used to drive the underwater end of the electric grid to move; the angle sensor is used to detect the posture information of the robot body; the depth sensor is used to detect the depth of the robot body; the infrared camera is used to collect the surrounding environment information of the robot body; the main control module is connected to the surface camera, left and right thrusters and the underwater robot, and is used to receive image information, angle information, depth information and position information sent back by the surface camera and the underwater robot, and use the mmsegmentation semantic segmentation algorithm to calculate the underwater environment picture and send it to the remote main control module; the remote control module is used to receive the picture and path information sent by the main control module to realize status monitoring and manual control of path setting functions.

[0008] Furthermore, the main control module uses the mmsegmentation semantic segmentation algorithm to calculate the underwater environment image in the following specific steps:

[0009] A1: Input stage, the underwater robot captures real-time images of the underwater environment through an infrared camera;

[0010] A2: In the pre-processing stage, noise reduction and image enhancement are performed on the captured image. The image enhancement uses histogram equalization, and its calculation formula is:

[0011]

[0012] Among them, I out (x,y) is the intensity value of the output image at point (x,y); I in (x,y) is the intensity value of the input image at point (x,y); L is the number of possible values ​​for the pixel intensity; N is the total number of pixels in the image. H(k) is the cumulative histogram, which represents the number of pixels with intensity value k or less;

[0013] A3: Semantic segmentation stage: The mmsegmentation semantic segmentation algorithm is used to perform semantic segmentation on the preprocessed image and divide the underwater environment in the image into different areas;

[0014] A4: Analysis phase: Based on the semantic segmentation results, obstacles in the underwater environment are identified and safe areas are marked;

[0015] A5: Output stage: outputs the semantic segmentation results and obstacle location information to the main control module and transmits them to the remote control module;

[0016] A6: During the obstacle avoidance phase, based on the output obstacle location information, the underwater robot body is controlled to move the underwater end of the electric fence and the left and right thrusters are controlled to move the surface end of the electric fence to avoid obstacles.

[0017] Furthermore, the semantic segmentation stage in step A3 specifically includes the following steps:

[0018] A31: Build a deep learning model and select a network architecture suitable for underwater image segmentation;

[0019] A32: Train the model using a labeled underwater image dataset until the model achieves the desired segmentation performance and the relevant evaluation indicators meet expectations.

[0020] A33: Model optimization, pruning and quantization operations on the trained model to adapt to the computing resources of the underwater robot.

[0021] Furthermore, in step A6, the method for controlling the underwater robot to avoid obstacles is: obtaining obstacle information based on semantic segmentation, combining the depth sensor and the angle sensor to provide movement parameters of the underwater robot, and then providing a path to avoid obstacles.

[0022] Furthermore, the main control module also has a dynamic path planning function, including the following steps:

[0023] B1: Input stage, the main control module receives the current position information of the underwater robot provided by the GPS module;

[0024] B2: Data processing phase: The main control module analyzes historical path data and identifies paths corresponding to areas with better underwater environmental conditions;

[0025] B3: Path planning stage: The main control module uses a dynamic programming algorithm to combine the current position information and the optimal solution of the local underwater environment to comprehensively calculate the optimal path;

[0026] B4: Output stage, the main control module outputs the calculated optimal path to the robot body;

[0027] B5: In the execution phase, the robot moves along the optimal path.

[0028] Furthermore, in step B3, the path planning stage specifically includes the following sub-steps:

[0029] B31: Define states, dividing the underwater environment into several states, each state representing a possible location;

[0030] B32: Define transitions, determine the rules and costs for transitioning from one state to another: Define a cost function C(s,a,s′), which represents the cost of transitioning from state s to state s′ through action a;

[0031] B33: Calculate the optimal path. Starting from the initial state, through iterative calculation, find the path with the minimum cost, that is, the optimal path. The mathematical formula for calculation is:

[0032]

[0033] Among them, V(s) is the value function of state s, which represents the minimum cost of reaching the target state from state s; A is the set of available actions, which represents all possible actions that can be taken from the current state s; C(s,a,s ′ ) is a transition from state s to state s through action a ′ The cost function is: γ is a discount factor that measures the current value of future rewards; V(s ′ ) is the state s ′ The value function represents the value of ′ The minimum cost to start reaching the goal state.

[0034] Furthermore, the middle and lower parts of the soft steel wire rope are fixed by glue sticks, thereby dividing the soft steel wire rope into three sections.

[0035] Furthermore, the infrared camera is provided with an LED light for fill light.

[0036] The beneficial effects of the present invention are as follows: the present invention designs a highly intelligent, effective, safe, low-cost, and easy-to-monitor and intervene intelligent electric fence and underwater robot collaborative fish-herding device. By using deep learning, semantic segmentation, GPS path planning and navigation, PID control and other algorithms, the present invention solves the problems of the device's weak ability to cope with complex underwater environments, low degree of automation, device monitoring and maintenance, and device safety. This device can promote the high-quality development of fisheries and has high practicality and promotion value. Specifically:

[0037] (1) The present invention performs semantic segmentation through the mmsegmentation algorithm, which can accurately identify obstacles in the underwater environment and improve the accuracy of obstacle avoidance.

[0038] (2) The present invention utilizes a dynamic programming algorithm combined with GPS module positioning to dynamically calculate the optimal path and improve the efficiency of driving fish.

[0039] (3) The present invention can adapt to complex underwater environments and has strong practicality and promotion value.

[0040] Other advantages, objects, and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art upon examination of the following description or may be learned from practice of the present invention. The objects and other advantages of the present invention may be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below with reference to the accompanying drawings, in which:

[0042] Figure 1 This is a structural diagram of an intelligent robot fish-herding device with path planning and underwater terrain recognition;

[0043] Figure 2 Schematic diagram of system connection relationship;

[0044] Figure 3 Schematic diagram of the connection relationship of device modules;

[0045] Figure numerals: generator 1, high-voltage pulse equipment 2, main control module 3, surface camera 4, buoy 5, left and right thrusters 6, soft steel wire rope 7, glue stick 8, underwater robot body 9, depth sensor 10, infrared camera 11, remote control module 12. DETAILED DESCRIPTION

[0046] The following describes the embodiments of the present invention by means of specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0047] Among them, the accompanying drawings are only for illustrative purposes and represent only schematic diagrams rather than actual pictures, and should not be understood as limiting the present invention. In order to better illustrate the embodiments of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the dimensions of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions may be omitted in the accompanying drawings.

[0048] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", "front", "back", etc. indicating directions or positional relationships, they are based on the directions or positional relationships shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0049] The present invention provides an intelligent robotic fish-herding device with path planning and underwater terrain recognition. The device consists of a remote control module, a main control module, and an underwater robot module. The remote control module, consisting of a touch screen and a Wi-Fi module, is wirelessly connected to the main control module via multi-level communication. It receives information sent back by the main control module in real time, allowing staff to monitor the device's operating status and perform manual intervention in a timely manner. The main control module integrates functional modules such as a power module, a Wi-Fi module, and a camera. It is connected to the underwater robot module via serial communication. It outputs a surface video stream based on images captured by the surface camera, calculates and outputs a semantically segmented video stream of the underwater environment based on images captured by the infrared camera, and performs SLAM underwater environment mapping when entering new waters. The underwater robot module consists of a robot controller composed of an infrared camera, a depth sensor, and an angle sensor, and the underwater robot body. It can detect the underwater robot's posture and depth, and receive obstacle avoidance commands sent back by the main control module based on the semantically segmented video stream to control the device's position, thereby achieving underwater obstacle avoidance.

[0050] The device works as follows: the underwater robot activates its thrusters to break the equilibrium between its gravity and the buoyancy of the float and dives to a certain depth. It then activates the electric fence and uses an infrared camera for target detection, steering the device toward the school of fish. To prevent the device from contacting underwater objects, an integrated depth sensor monitors the current water depth in real time. If the device reaches the bottom depth, it immediately propels the device upwards. A PID algorithm is used to control the device's water depth within a certain range. To address complex underwater terrain, the robot uses its infrared camera to transmit images back to the main control module for semantic segmentation of the underwater environment. When a relatively high surface area is detected, the robot decelerates and simultaneously ascends, ultimately achieving flexible underwater obstacle avoidance. To prevent short circuits caused by the end electric fences being too close, the robot regularly measures the distance between the fences. When the distance between the fences reaches the critical contact point, the robot advances the float and tightens the fence until it reaches a safe distance. During initial operation, the device will autonomously navigate within the waters based on GPS feedback indicating the boundaries of the waters, providing a reference for path planning. The device can also integrate with a GPS positioning module. Once the remote control module sets the path, the device will then operate along the established path. Simultaneously, the device's path will be fed back to the remote control module in real time, facilitating route planning for the next operation. After multiple operations, the system will record the device's path and utilize a dynamic programming algorithm to determine the optimal path for repelling fish. To address the inability of existing repelling devices to monitor their operation in real time, this device can also feed the surface camera video stream and the underwater environment video stream output by the infrared camera, after running a semantic segmentation algorithm, back to the remote control module, facilitating real-time control of the device and prompt human intervention.

[0051] like Figure 1 As shown, the device specifically includes the following structure:

[0052] Generator 1: Powers the entire system, including the electric grid, electric thrusters, and underwater robot. Considering the high-voltage pulse equipment requires approximately 300W of power, and other power-consuming devices require approximately 300W, the entire system requires approximately 600W of power. A generator with a power consumption of less than 1kW, such as the Honda EU1000i, is suitable.

[0053] High-voltage pulse equipment 2: Input 220V voltage to generate 300V-500V high-voltage pulses, and the positive and negative poles of the high-voltage pulses are applied to the four soft steel wire ropes 7. The equipment can use a Tester voltage pulse generator, etc.

[0054] Main Control Module 3: An embedded system integrating a power module, Wi-Fi module, and GPS module. It connects to the surface camera 4 and transmits its image and device location in real time. It also runs a deep learning semantic segmentation algorithm, connects to the underwater robot via a serial port, and analyzes the underwater robot's infrared camera image and other information. It then outputs the resulting semantic segmentation image of the underwater environment, enabling underwater obstacle avoidance. The embedded system can use the JETSON NANO, the Wi-Fi module can use a LiChuang module, and the GPS module can use the Shenzhen Hefangyuan GU620.

[0055] Surface camera 4: connected to the main control module, used to monitor the water surface conditions.

[0056] Float 5: Makes the main control module of the device and the underwater robot in the initial state float on the water surface. The buoy on the surface is used to place and protect the main control module. The buoy under the water allows the underwater robot module to break the current balance of gravity and buoyancy with the water surface as the reference and start to float down, constantly correcting the working posture of the electric grid.

[0057] Left and right thrusters 6: These propel the vehicle across the water, utilizing differential speeds to achieve turns. Examples include the BlueRobotics T200 Thruster thruster.

[0058] Electric fence and connecting cable: The electric fence is composed of soft steel wire rope 7 with positive and negative poles, alternating from left to right. An electric field is formed between the positive and negative poles of the electric fence, which stimulates fish. The length of the electric fence can be determined based on the actual conditions of the water area. For example, in a reservoir setting, at a water depth of 15 meters, the electric fence can be designed with an upper section of 6 meters, a middle section of 7 meters, and a lower section of 2 meters, separated by two rubber rods. At a water depth of 10 meters, the upper section can be 4 meters, a middle section of 5 meters, and a lower section of 1 meter. The connecting cable connects the main control module and the underwater robot module, similar to the wiring of the electric fence. Products such as Kencove can be used for the electric fence, and products such as Oriental Cable Group can be used for the connecting cable.

[0059] Glue stick 8: Two glue sticks are set in the middle of the electric grid to prevent the electric grid from short-circuiting. On the other hand, they partially fix the routing of the electric grid and the connecting cable to prevent the electric grid or the connecting cable from getting entangled during the movement of the underwater robot.

[0060] The underwater robot includes components such as the robot body 9, an angle sensor, a depth sensor 10, a GPS module, and an infrared camera 11. It connects to the main control module to transmit parameters in real time, enabling electric barrier obstacle avoidance control. The angle sensor can be the PCF8591 rotation angle sensor. The depth sensor 10 is used to measure the underwater robot's depth (usually also the depth of the electric barrier device's end), providing depth parameter support for electric barrier obstacle avoidance. The Shenzhen Huace HC-200 depth sensor can be used as the depth sensor. The infrared camera 11 is used to output a video stream of the underwater environment. Underwater environments are typically dimly lit and turbid, making them difficult to clearly identify. Therefore, an infrared camera with LED fill light is used. The infrared camera can be the Hikvision DS-2CD6886G0-CO (8mm).

[0061] Remote control module 12: It is composed of a touch screen and a WIFI module powered by a lithium battery module. It receives the image, path and other information sent back by the main control module via WIFI in real time, making it easy to realize functions such as device operation status monitoring, path planning, and manual intervention.

[0062] like Figure 2 The figure shows the system connection relationship. The device mainly consists of three core modules: remote control module, main control module and underwater robot module. The main control module is also responsible for controlling the operation of the pulse fish chasing module. Figure 3 As shown in the figure, the remote control module mainly consists of a lithium battery module, a touch screen display, and a WiFi module. The lithium battery module is responsible for power supply, the WiFi module is responsible for communication with the main control module, and the touch screen is responsible for visual interaction. The main control module consists of six parts: a power module, a main controller (i.e., an embedded system), a WiFi module, a GPS module, a camera, and left and right underwater propulsion. It is also connected to the pulse fish chasing module. The pulse fish chasing module includes a high-voltage pulse device and an electric grid, which completes the working voltage conversion and operation of the electric grid. The main controller is connected to the robot controller and is responsible for using model algorithms for calculation and reasoning, and outputting appropriate signals to related equipment. The WiFi module is responsible for establishing communication with the remote control module. The GPS module is responsible for real-time positioning of the device, helping to visualize the device's operating path and providing a reference for staff decision-making and dynamic planning of the optimal path.

[0063] The underwater robot module consists of the robot itself and a robot controller that integrates an LED infrared camera, an angle sensor, and a depth sensor. The LED infrared camera is responsible for capturing images in low-light and complex underwater conditions; the angle sensor is responsible for detecting the robot's current posture, ensuring it maintains a forward position; and the depth sensor is responsible for detecting the robot's current depth (usually approximately the depth of the electric fence). Combined with the infrared camera's semantic segmentation of the underwater situation, the robot's thrusters are activated in a timely manner, driving the device to the surface and maintaining a safe water depth.

[0064] The main control module's power supply is turned on, followed by the remote control module. The surface camera and the infrared camera of the underwater robot module transmit video streams. If the video stream indicates normal device status, the underwater robot's thrusters begin operating, breaking the balance between the buoyancy of the device's end float and its own weight and beginning to dive. Once the device reaches the lower limit of the predetermined safe depth, the underwater robot's thrusters and the left and right thrusters controlled by the main control module begin to operate at the same speed, propelling the entire device along the path set by the remote control module. If a turn is required, the left and right thrusters can be made to generate different speeds for differential turning. The underwater robot also adjusts its thruster speed to align with the left and right thrusters. Simultaneously, algorithms such as environment semantic segmentation, depth monitoring, and PID control in the main control module begin running, ensuring that the speeds of the left and right thrusters and the underwater robot's thrusters are as close as possible to each other, allowing the device to operate in an appropriate posture. The main control module also monitors the underwater environment, the device's depth, and the working conditions of the electric fence in real time to ensure normal operation. Staff use a remote control module to monitor the device's operation in real time via above- and underwater cameras. The GPS module also monitors whether the device's trajectory is normal and whether it is operating within the water's boundaries, allowing for timely switching between automatic and manual modes to intervene in emergencies. Once the device completes its intended operation, it automatically stops.

[0065] In addition, when the underwater robot detects that the distance between the end electric grids has reached a dangerous distance, it controls the underwater robot to accelerate, thereby driving the buoy at the end of the electric grid to move forward and tighten the electric grid, thereby increasing the distance between the electric grids until the distance between the electric grids remains within a safe distance within a certain period of time. The PID control algorithm is then used to slowly restore the underwater robot to the same speed as the left and right underwater thrusters.

[0066] The underwater robot module's infrared camera with LED imaging is clear and bright under LED fill light, which can effectively deal with conditions such as turbid river water and high sediment content. When the river water is too turbid and the collected video signal is blurred, the device's safe water depth range is increased by a certain value, allowing the device to operate according to the given optimal path.

[0067] The steps of the above-mentioned mmsegmentation semantic segmentation algorithm for underwater robot obstacle avoidance are as follows:

[0068] A1: Input stage, the underwater robot captures real-time images of the underwater environment through an infrared camera;

[0069] A2: In the pre-processing stage, noise reduction and image enhancement are performed on the captured image. The image enhancement uses histogram equalization, and its calculation formula is:

[0070]

[0071] Among them, I out (x,y) is the intensity value of the output image at point (x,y); I in (x,y) is the intensity value of the input image at point (x,y); L is the number of possible values ​​for the pixel intensity; N is the total number of pixels in the image. H(k) is the cumulative histogram, which represents the number of pixels with intensity value k or less;

[0072] A3: Semantic segmentation stage: The mmsegmentation semantic segmentation algorithm is used to perform semantic segmentation on the preprocessed image, dividing the underwater environment in the image into different areas. Specifically, it includes:

[0073] A31: Build a deep learning model and select a network architecture suitable for underwater image segmentation;

[0074] A32: Train the model using a labeled underwater image dataset until the model achieves the desired segmentation performance and the relevant evaluation indicators meet expectations.

[0075] A33: Model optimization, pruning and quantizing the trained model to adapt to the computing resources of the underwater robot;

[0076] A4: Analysis phase: Based on the semantic segmentation results, obstacles in the underwater environment are identified and safe areas are marked;

[0077] A5: Output stage: outputs the semantic segmentation results and obstacle location information to the main control module and transmits them to the remote control module;

[0078] A6: During the obstacle avoidance phase, based on the output obstacle location information, the underwater robot body is controlled to move the underwater end of the electric grid and the left and right thrusters to move the surface end of the electric grid to avoid obstacles. Specifically, the obstacle information is obtained through semantic segmentation, and the underwater robot movement parameters are determined by combining the depth sensor and angle sensor, thereby determining a path to avoid the obstacles.

[0079] The main control module also has a dynamic path planning function, which includes the following steps:

[0080] B1: Input stage, the main control module receives the current position information of the underwater robot provided by the GPS module;

[0081] B2: Data processing phase: The main control module analyzes historical path data and identifies paths corresponding to areas with better underwater environmental conditions;

[0082] B3: Path planning: The main control module uses a dynamic programming algorithm to combine the current position information and the optimal solution of the local underwater environment to comprehensively calculate the optimal path. This includes the following sub-steps:

[0083] B31: Define states, dividing the underwater environment into several states, each state representing a possible location;

[0084] B32: Define transitions, determine the rules and costs for transitioning from one state to another: Define a cost function C(s,a,s′), which represents the cost of transitioning from state s to state s′ through action a;

[0085] B33: Calculate the optimal path. Starting from the initial state, through iterative calculation, find the path with the minimum cost, that is, the optimal path. The mathematical formula for calculation is:

[0086]

[0087] Among them, V(s) is the value function of state s, which represents the minimum cost of reaching the target state from state s; A is the set of available actions, which represents all possible actions that can be taken from the current state s; C(s,a,s ′ ) is a transition from state s to state s through action a ′ The cost function is: γ is a discount factor that measures the current value of future rewards; V(s ′ ) is the state s ′ The value function represents the value of ′ The minimum cost to start reaching the goal state;

[0088] B4: Output stage, the main control module outputs the calculated optimal path to the robot body;

[0089] B5: In the execution phase, the robot moves along the optimal path.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent robot fish-herding device with path planning and underwater terrain recognition, characterized by: The electric fence comprises an electric fence including a surface end floating on the water surface and an underwater end connected to multiple underwater robots for underwater travel; the surface end and the underwater end are connected by multiple rows of soft steel wire ropes; the surface end is equipped with a generator, a high-voltage pulse device, a main control module, a surface camera, and left and right thrusters; the underwater robot at the underwater end includes a robot body, an angle sensor, a depth sensor, a GPS module, and an infrared camera; and also includes a remote control module; The generator is used to supply power to each device module; the high-voltage pulse equipment is used to apply high-voltage pulse current to the soft steel wire rope; the surface camera is used to collect surface images; the robot body is used to drive the underwater end of the electric grid to move; the angle sensor is used to detect the posture information of the robot body; the depth sensor is used to detect the depth of the robot body; the infrared camera is used to collect the surrounding environment information of the robot body; the main control module is connected to the surface camera, left and right thrusters and the underwater robot, and is used to receive image information, angle information, depth information and position information sent back by the surface camera and the underwater robot, and use the mmsegmentation semantic segmentation algorithm to calculate the underwater environment picture and send it to the remote main control module; the remote control module is used to receive the picture and path information sent by the main control module to realize status monitoring and manual control of path setting functions.

2. The intelligent robot fish-herding device with path planning and underwater terrain recognition according to claim 1 is characterized in that: The specific steps of the main control module using the mmsegmentation semantic segmentation algorithm to calculate the underwater environment image are as follows: A1: Input stage, the underwater robot captures real-time images of the underwater environment through an infrared camera; A2: In the pre-processing stage, noise reduction and image enhancement are performed on the captured image. The image enhancement uses histogram equalization, and its calculation formula is: Among them, I out (x,y) is the intensity value of the output image at point (x,y); I in (x,y) is the intensity value of the input image at point (x,y); L is the number of possible values ​​for the pixel intensity; N is the total number of pixels in the image. H(k) is the cumulative histogram, which represents the number of pixels with intensity value k or less; A3: Semantic segmentation stage: The mmsegmentation semantic segmentation algorithm is used to perform semantic segmentation on the preprocessed image and divide the underwater environment in the image into different areas; A4: Analysis phase: Based on the semantic segmentation results, obstacles in the underwater environment are identified and safe areas are marked; A5: Output stage: outputs the semantic segmentation results and obstacle location information to the main control module and transmits them to the remote control module; A6: During the obstacle avoidance phase, based on the output obstacle location information, the underwater robot body is controlled to move the underwater end of the electric fence and the left and right thrusters are controlled to move the surface end of the electric fence to avoid obstacles.

3. The intelligent robot fish-herding device with path planning and underwater terrain recognition according to claim 2 is characterized in that: The semantic segmentation stage described in step A3 specifically includes the following steps: A31: Build a deep learning model and select a network architecture suitable for underwater image segmentation; A32: Train the model using a labeled underwater image dataset until the model achieves the desired segmentation performance and the relevant evaluation indicators meet expectations. A33: Model optimization, pruning and quantization operations on the trained model to adapt to the computing resources of the underwater robot.

4. The intelligent robot fish-herding device with path planning and underwater terrain recognition according to claim 2 is characterized in that: In step A6, the method for controlling the underwater robot to avoid obstacles is: obtaining obstacle information based on semantic segmentation, combining the depth sensor and the angle sensor to provide movement parameters of the underwater robot, and then providing a path to avoid obstacles.

5. The intelligent robot fish-herding device with path planning and underwater terrain recognition according to claim 1 is characterized in that: The main control module also has a dynamic path planning function, including the following steps: B1: Input stage, the main control module receives the current position information of the underwater robot provided by the GPS module; B2: Data processing phase: The main control module analyzes historical path data and identifies paths corresponding to areas with better underwater environmental conditions; B3: Path planning stage: The main control module uses a dynamic programming algorithm to combine the current position information and the optimal solution of the local underwater environment to comprehensively calculate the optimal path; B4: Output stage, the main control module outputs the calculated optimal path to the robot body; B5: In the execution phase, the robot moves along the optimal path.

6. The intelligent robot fish-herding device with path planning and underwater terrain recognition according to claim 5 is characterized in that: In step B3, the path planning stage specifically includes the following sub-steps: B31: Define states, dividing the underwater environment into several states, each state representing a possible location; B32: Define transitions, determine the rules and costs for transitioning from one state to another: Define a cost function C(s,a,s′), which represents the cost of transitioning from state s to state s′ through action a; B33: Calculate the optimal path. Starting from the initial state, through iterative calculation, find the path with the minimum cost, that is, the optimal path. The mathematical formula for calculation is: Among them, V(s) is the value function of state s, which represents the minimum cost of reaching the target state from state s; A is the set of available actions, which represents all possible actions that can be taken from the current state s; C(s,a,s ′ ) is a transition from state s to state s through action a ′ The cost function is: γ is a discount factor that measures the current value of future rewards; V(s ′ ) is the state s ′ The value function represents the value of ′ The minimum cost to start reaching the goal state.

7. The intelligent robot fish-herding device with path planning and underwater terrain recognition according to claim 1 is characterized in that: The middle and lower parts of the soft steel wire rope are fixed by glue sticks, thereby dividing the soft steel wire rope into three sections.

8. The intelligent robot fish-herding device with path planning and underwater terrain recognition according to claim 1 is characterized in that: The infrared camera is provided with an LED light for fill light.

Images