Autonomous underwater robot and motion control method thereof

Abstract

The invention provides an autonomous underwater robot and a motion control method thereof.The autonomous underwater robot is used for collecting training data of swimmers, the autonomous underwater robot comprises a supporting frame, a watertight compartment is installed in the middle of the supporting frame, and propellers distributed in the circumferential direction of the watertight compartment at intervals are installed in the four corners of the supporting frame; wherein a core control unit is mounted in the watertight compartment, the core control unit comprises a core controller, the core controller is connected with an upper computer through a communication module, a PID (Proportion Integration Differentiation) controller is arranged in the core controller, and a color identification module is arranged in the upper computer; the autonomous underwater robot has the advantages that two tracking modes of manual control and automatic control are provided, in the automatic control mode, the PID controller is combined with the OpenCV color recognition technology, the autonomous underwater robot can track swimming athletes in real time, a more continuous and complete underwater visual angle is provided for coaches, and the swimming athletes can be tracked in real time. And the skill actions of the athletes can be analyzed more deeply.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater robots, and in particular to an autonomous underwater robot and a motion control method thereof. Background Art

[0002] Swimming is a complex competitive sport, and the details of an athlete's movements and postures have a great impact on his or her performance. During training, coaches need to accurately observe and analyze the athlete's underwater movements. However, due to surface reflections and current interference, it is difficult to obtain a complete underwater perspective by observing from the water surface or the side of the pool. Traditional videos shot from the water surface cannot provide a clear perspective due to interference from surface splashes and currents, making it impossible for coaches to fully grasp the athlete's technical movements.

[0003] Currently, the common pool cleaning robots and pool bottom cameras on the market have certain limitations; the pool cleaning robots are designed to clean the pool bottom and are usually equipped with a simple navigation system and cleaning function, but they are poor in speed and maneuverability, and it is difficult to meet the needs of real-time tracking of athletes. At the same time, this type of robot cannot provide high-definition real-time images, so it is not suitable for posture analysis in sports training; the pool bottom fixed camera is fixedly installed on the bottom of the pool and can provide a certain underwater perspective, but is limited to a fixed position and can only capture a limited perspective. It cannot flexibly follow the movement of the athlete and can usually only provide shooting from a single angle. Therefore, the coach can only obtain limited underwater images and cannot fully capture the athlete's dynamic movements; these technologies limit the coach's comprehensive grasp of the athlete's real-time status, thereby affecting the optimization of training results. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide an autonomous underwater robot and a motion control method thereof, so as to solve the problem that the existing technology and equipment limit the coach's comprehensive grasp of the real-time status of the swimmers, thereby affecting the optimization of the training effect.

[0005] To achieve the above objectives and other related objectives, the present invention provides the following technical solutions:

[0006] An autonomous underwater robot is used to collect training data of swimmers, comprising a support frame, a watertight compartment is installed at the middle position of the support frame, and thrusters are installed at four corners of the support frame and are distributed at intervals along the circumference of the watertight compartment; wherein a high-definition camera and a core control unit are installed in the watertight compartment, the core control unit comprises a core controller and a communication module connected to the core controller, the core controller is also connected to the thruster, the core controller is connected to the high-definition camera through a switch, the core controller is connected to a host computer through the communication module, a PID controller is provided in the core controller, and a color recognition module is provided in the host computer.

[0007] In one embodiment of the present invention, the watertight compartment includes a protective cylinder and a protective cover installed on the protective cylinder through a flange, a sealing ring is also provided between the protective cylinder and the protective cover, the core control unit and the converter are both installed in the protective cylinder, a wiring board and a wiring box are also provided in the protective cylinder, and the high-definition camera is installed in the protective cover.

[0008] In one embodiment of the present invention, the core control unit adopts an Arduino Mega 2560 core circuit board, and the core control unit can also be connected to a network expansion board, and the network expansion board adopts a W5100S network expansion board, and the network expansion board is also connected to the thruster.

[0009] A motion control method for an autonomous underwater robot. The method is based on the autonomous underwater robot and comprises the following steps: obtaining a control mode selected by a user, and controlling the motion of the autonomous underwater robot according to the control mode selected by the user, wherein the control mode comprises a manual control mode and an automatic control mode.

[0010] In one embodiment of the present invention, the use of a manual control mode to control the movement of an autonomous underwater robot includes: a user presses the "WASD" keys on a host computer keyboard, and the host computer sends instructions corresponding to each key to the autonomous underwater robot, wherein the "WASD" keys on the keyboard correspond to controlling the autonomous underwater robot to move forward, backward, turn left, and turn right; a user may also input a speed gear of the propeller through the keyboard, and the host computer sends instructions corresponding to the speed gear to the autonomous underwater robot; after the core controller in the autonomous underwater robot receives the key instructions and speed gear instructions sent by the host computer through a communication module, it controls the four propellers according to the key instructions and speed gear instructions, so that the autonomous underwater robot moves forward, backward, turns left, and turns right at the speed gear.

[0011] In one embodiment of the present invention, the autonomous underwater robot is controlled to perform forward and backward and turning movements by the four thrusters; when the autonomous underwater robot moves forward, thruster one and thruster two rotate forward, and thruster three and thruster four rotate reversely; when the autonomous underwater robot moves backward, thruster one and thruster two rotate reversely, and thruster three and thruster four rotate forward.

[0012] In one embodiment of the present invention, the use of an automatic control mode to control the movement of an autonomous underwater robot includes: the host computer obtains an underwater video of a swimmer captured by a high-definition camera, and extracts video frames from the underwater video for color detection through a color recognition module, determines the center position coordinates of the swimmer according to the color detection result, and sends the center position coordinates to the autonomous underwater robot; after the core controller in the autonomous underwater robot receives the center position coordinates sent by the host computer through a communication module, the PID controller determines the speed and direction of each propeller according to the center position coordinates, and controls the four propellers according to the speed and direction of each propeller to keep the swimmer always in the center position of the high-definition camera, thereby realizing real-time tracking and high-definition shooting of the swimmer.

[0013] In one embodiment of the present invention, the color recognition module is the HSV color space of OpenCV, and the video frame is extracted from the underwater video through the HSV color space of OpenCV to perform color detection, and the center position coordinates of the swimmer are determined according to the color detection result.

[0014] In one embodiment of the present invention, the video frames are extracted from the underwater video through the HSV color space of OpenCV for color detection, and the center position coordinates of the swimmer are determined according to the color detection results, including: extracting video frames from the video of the swimmer underwater captured by a high-definition camera, and converting the video frames into the HSV color space, wherein the HSV color space is more suitable for color detection; by defining the HSV range of the target color, a mask is generated to isolate the specified color area, and after optimizing the mask quality by morphological operations, the boundary of the color area is determined by contour detection, and the noise area within the color area is filtered out; the center of mass of each contour is calculated, and the center point of the main target is obtained by weighted averaging, and the coordinates of the center point are converted into a new coordinate system with the center of the video frame as the origin, thereby obtaining the center position coordinates of the swimmer.

[0015] In one embodiment of the present invention, the PID controller adopts a PID control algorithm to calculate the deviation between the current state and the target state of the autonomous underwater robot and adjust the control output according to the deviation, thereby achieving precise control of the dynamic characteristics of the autonomous underwater robot; wherein the PID control algorithm includes a proportional unit, an integral unit and a differential unit related to the deviation.

[0016] As described above, the autonomous underwater robot and the motion control method thereof of the present invention have the following beneficial effects:

[0017] The present invention provides two tracking modes, manual control and automatic control, which not only meet the flexible operation requirements in specific situations, but also ensure the automation requirements in daily training, and provide more choices for different training scenarios; in the manual control mode, the user can control the autonomous underwater robot through the host computer, so that it can move freely and follow the swimmer in real time; in the automatic control mode, by using the PID controller combined with the color recognition technology of OpenCV, the autonomous underwater robot can accurately lock the position of the swimmer, and automatically adjust its own movement to keep the swimmer always in the center position of the camera, which provides the coach with a more continuous and complete underwater perspective, which not only helps to analyze the athlete's technical movements more deeply, but also optimizes the training effect and improves the training quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a top-down perspective schematic diagram of an autonomous underwater robot disclosed in an embodiment of the present invention;

[0019] Figure 2 It is a left front perspective schematic diagram of the autonomous underwater robot disclosed in an embodiment of the present invention;

[0020] Figure 3 is a schematic top view of an autonomous underwater robot disclosed in an embodiment of the present invention;

[0021] Figure 4 It is a schematic diagram of the connection between the autonomous underwater robot and the host computer in the autonomous underwater robot disclosed in the embodiment of the present invention;

[0022] Figure 5 It is a schematic diagram of the overall circuit principle of the autonomous underwater robot disclosed in the embodiment of the present invention;

[0023] Figure 6 is a structural block diagram of the entire autonomous underwater robot disclosed in an embodiment of the present invention;

[0024] Figure 7A physical schematic diagram of an Arduino Mega 2560 core circuit board (left) and a thruster (right) in an autonomous underwater robot disclosed in an embodiment of the present invention;

[0025] Figure 8 It is a physical schematic diagram of a watertight compartment in an autonomous underwater robot disclosed in an embodiment of the present invention;

[0026] Fig. 9 It is a wiring diagram of a thruster in an autonomous underwater robot disclosed in an embodiment of the present invention;

[0027] Fig.10 It is a physical schematic diagram of the W5100S network expansion board in the autonomous underwater robot disclosed in the embodiment of the present invention;

[0028] Fig.11 It is a schematic diagram of the overall flow of the manual control mode in the motion control method of the autonomous underwater robot disclosed in the embodiment of the present invention;

[0029] Fig.12 It is a schematic diagram of the overall flow of the automatic control mode in the motion control method of the autonomous underwater robot disclosed in the embodiment of the present invention;

[0030] Fig.13 It is a schematic diagram of the color recognition effect obtained by using the HSV color space of OpenCV in the motion control method of the autonomous underwater robot disclosed in the embodiment of the present invention;

[0031] Fig.14 This is a picture of an autonomous underwater robot working in water in the motion control method of an autonomous underwater robot disclosed in an embodiment of the present invention.

[0032] Component number description

[0033] 1. Autonomous underwater robot; 11. Support frame; 12. Watertight compartment; 121. Protective tube; 122. Protective cover; 13. Propeller. DETAILED DESCRIPTION

[0034] The following specific embodiments illustrate the implementation of the present invention, and those familiar with the technology can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0035] The first embodiment of the present invention relates to an autonomous underwater robot, see Figures 1 to 10 , used to collect training data of swimmers, including a support frame 11, a watertight compartment 12 is installed in the middle of the support frame 11, and the actual picture is as follows Figure 8As shown, the watertight compartment 12 includes a protective tube 121 and a protective cover 122 installed on the protective tube 121 through a flange, and a sealing ring is also provided between the protective tube 121 and the protective cover 122, wherein the protective tube 121 is cylindrical in shape, and the protective cover 122 is hemispherical in shape. The watertight compartment 12 is used to protect the electronic components inside the autonomous underwater robot 1 to prevent water from entering during underwater operations; the SOLIDWORKS fluid simulation tool is used to perform resistance analysis on the watertight compartment 12, and the initial cube design is improved to a cylindrical design due to excessive resistance, so as to reduce the fluid resistance underwater, thereby improving movement flexibility. During the assembly process, the watertight compartment 12 is also tested to ensure that it will not enter water during underwater operations.

[0036] See also Figures 1 to 3 , Figure 7 and 9 The four corners of the support frame 11 are equipped with thrusters 13 distributed along the circumferential interval of the watertight compartment 12, wherein four thrusters 13 are respectively installed at the four corners of the support frame 11 (left front, right front, left rear, right rear), and the four thrusters 13 are used to control the autonomous underwater robot 1 to move forward, backward and turn.

[0037] like Figures 4 to 7 As shown, a core control unit is installed in the protective tube 121. In this embodiment, the core control unit in the autonomous underwater robot 1 adopts an Arduino Mega 2560 core circuit board. For details, please refer to Figure 7 , the shore power supply system is used to provide power to the autonomous underwater robot 1. Figure 4 and Figure 5 In the figure, the autonomous underwater robot 1 is connected to the host computer and the power supply through a zero buoyancy line; the core control unit includes an Arduino controller and a communication module, the Arduino controller is connected to four thrusters 13 through PWM signal lines, and a PID controller is arranged in the Arduino controller, wherein the Arduino controller controls the speed and direction of each thruster 13 by outputting a PWM signal, the PWM signal range of the thruster 13 is 1100-1500-1900 μs, and the PWM signal received by each thruster 13 is adjusted according to the feedback of the PID controller to achieve smooth automatic tracking, so as to keep the swimmer in the center of the high-definition camera screen, thereby achieving precise control of the autonomous underwater robot 1.

[0038] like Figure 5 , Figure 6 and Fig.10As shown, a high-definition camera for capturing underwater images of swimmers is installed in the protective cover 122, the Arduino controller is connected to the high-definition camera through a switch, and the converter is also installed in the protective tube 121, wherein the high-definition camera is connected to the switch through a network port, and the switch is connected to the Arduino controller; the Arduino controller is connected to the host computer through a communication module, and a color recognition module is provided in the host computer, wherein the communication between the host computer and the slave computer adopts the UDP protocol, which has the advantages of low latency and fast transmission, and is helpful to realize real-time video transmission and command control, and the autonomous underwater robot 1, that is, the slave computer, transmits data with the host computer through the UDP protocol, and the wiring follows the T568B line sequence, and the host computer can receive video images and send commands to the Arduino controller to realize manual operation and monitoring; the Arduino controller is equipped with a W5100S network expansion board, and the W5100S network expansion board communicates with the host computer through the SPI protocol through UDP, and the W5100S network expansion board is also connected to the thruster 13 through a PWM signal line, for details, please refer to Fig.10 .

[0039] The second embodiment of the present invention relates to a motion control method of an autonomous underwater robot. The method is based on the autonomous underwater robot 1. Fig.11 and Fig.12 , as follows:

[0040] Obtaining a control mode selected by the user, and controlling the movement of the autonomous underwater robot 1 according to the control mode selected by the user, wherein the control mode includes a manual control mode and an automatic control mode, and the user can independently select the manual control mode or the automatic control mode on the host computer;

[0041] Specifically, the manual control mode is used to control the movement of the autonomous underwater robot 1, including:

[0042] Step 101, the user presses the "WASD" key on the upper computer keyboard, and the upper computer sends the command corresponding to each key to the autonomous underwater robot 1, wherein the "WASD" key on the keyboard controls the autonomous underwater robot 1 to move forward, backward, turn left and turn right; the user can also input the speed gear of the propeller 13 through the keyboard, and the upper computer sends the command corresponding to the speed gear to the autonomous underwater robot 1;

[0043] Step 102, after receiving the key command and speed gear command sent by the host computer through the communication module, the core controller in the autonomous underwater robot 1 controls the four thrusters 13 according to the key command and speed gear command, so that the autonomous underwater robot 1 moves forward, backward, turns left and turns right at the speed gear. For details, please refer to Fig.11 ;

[0044] It should be noted that the four thrusters 13 can be recorded as FL, FR, BL and BR, and the autonomous underwater robot 1 is controlled by the four thrusters 13 to perform forward, backward and turning movements; when the autonomous underwater robot 1 moves forward, thruster 1 FL and thruster 2 FR rotate forward, and thruster 3 BL and thruster 4 BR rotate reversely; when the autonomous underwater robot 1 moves backward, thruster 1 FL and thruster 2 FR rotate reversely, and thruster 3 BL and thruster 4 BR rotate forward; clockwise rotation causes thruster 1 FL and thruster 4 BR to rotate forward; counterclockwise rotation causes thruster 2 FR and thruster 3 BL to rotate forward, thereby achieving multi-directional movement; manual control can be achieved by using WASD on the keyboard, and Q can be pressed to force a stop; automatic control is performed based on the data read by the high-definition camera, and a function can also be disabled by adjustment in the software interface.

[0045] More specifically, the motion of the autonomous underwater robot 1 is controlled using the automatic control mode, including:

[0046] Step 201, the host computer obtains an underwater video of a swimmer captured by a high-definition camera, extracts video frames from the underwater video for color detection through a color recognition module, determines the center position coordinates of the swimmer according to the color detection result, and sends the center position coordinates to the autonomous underwater robot 1;

[0047] It should be noted that the color recognition module is the HSV color space of OpenCV. The video frames are extracted from the underwater video through the HSV color space of OpenCV for color detection. The coordinates of the center position of the swimmer are determined according to the color detection results. The specific steps are as follows: first, the video frames are extracted from the underwater video of the swimmer captured by the high-definition camera and converted into the HSV color space, because HSV is more suitable for color detection; then, by defining the HSV range of the target color (for example, red), a mask is generated to isolate the specified color area, and after optimizing the mask quality by morphological operations (such as dilation), the boundary of the color area is found through contour detection, and the noise area (contours with smaller areas) is filtered out; then the centroid of each contour is calculated, and the center point of the main target is obtained by weighted averaging; finally, the coordinates of this center point are converted to a new coordinate system with the center of the video frame as the origin, and sent to the lower computer in real time through the UDP protocol. At the same time, the target position can be marked on the screen for debugging and visualization. This process requires real-time processing and dynamic adjustment of the color range to adapt to environmental lighting and color changes. Please refer to Fig.13; Therefore, it can be seen from the above that the upper computer uses the HSV color space of OpenCV for color recognition to detect the brightly colored (for example, red) swimsuits worn by swimmers, determines the center position coordinates of the swimmers through color recognition, and transmits the coordinates to the lower computer (that is, the autonomous underwater robot 1), and the lower computer uses these coordinate information to control the speed and direction of the four thrusters 13, so that the autonomous underwater robot 1 can continue to follow the athlete.

[0048] Step 202: After the core controller in the autonomous underwater robot 1 receives the center position coordinates sent by the host computer through the communication module, the PID controller determines the speed and direction of each propeller 13 according to the center position coordinates, and controls the four propellers 13 according to the speed and direction of each propeller 13 to keep the swimmer always in the center position of the high-definition camera, so as to achieve real-time tracking and high-definition shooting of the swimmer. For details, please refer to Fig.12 ;

[0049] It should be noted that the PID controller adopts the PID control algorithm, which calculates the deviation between the current state and the target state of the autonomous underwater robot 1 and adjusts the control output according to the deviation, thereby realizing precise control of the dynamic characteristics of the autonomous underwater robot 1; in the linear PID control algorithm, there are proportional units, integral units and differential units Kp, Ki, Kd related to the deviation. The deviation is reduced until it is eliminated through the mutual linkage adjustment of the three. ArduinoIDE provides the PID_v2.h library for PID control; after being processed by the host computer, the host computer will transmit an x-coordinate to the lower computer. The coordinate is based on the position of the high-definition camera as the origin and the direction of movement of the swimmer as the positive coordinate of the x-axis. After receiving the coordinate, the automatic tracking program will perform a calculation to obtain an Output, and then map the Output to 1100-1900 through linear mapping, and use it as a PWM signal to control the speed of the propeller 13; by reasonably setting the values ​​of Kp, Ki, and Kd, the tracking function can be better completed.

[0050] Specifically, the working process of the autonomous underwater robot 1 is as follows: Startup and initialization: After the autonomous underwater robot 1 is started, the Arduino controller, high-definition camera, communication module and propeller 13 are initialized first, wherein the lights of the Arduino controller, high-definition camera and communication module will light up, and the propeller 13 will make a prompt sound; Manual control mode: In manual control mode, the user controls the propeller 13 through the "WASD" keys of the host computer to adjust the movement direction and speed of the robot; Automatic tracking mode: When switched to automatic control mode, the high-definition camera starts to collect real-time video of the swimmer, locates the center position of the swimmer through color recognition, and then adjusts the action of the propeller 13 according to the position information, so that the autonomous underwater robot 1 continues to follow the swimmer, please refer to Fig.14 ; Real-time data transmission: Video data and control instructions are transmitted through UDP communication to achieve real-time interaction between the host computer and the slave computer.

[0051] In summary, the present invention provides two tracking modes, manual control and automatic control, which not only meet the flexible operation requirements in specific situations, but also ensure the automation requirements in daily training, providing more options for different training scenarios; the autonomous underwater robot 1 is designed to provide high-definition underwater images, which are better than the image quality provided by many existing solutions, and help coaches observe the athletes' movements more carefully; unlike traditional swimming pool cleaning robots and fixed cameras on the bottom of the pool, the autonomous underwater robot 1 has a high degree of flexibility and maneuverability, can move freely and follow swimmers in real time, thereby providing a wider range of angles and perspectives, not limited to observations on the bottom of the pool or a fixed point.

[0052] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. All equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An autonomous underwater robot for collecting training data of a swimmer, comprising a support frame (11), characterized in that: A watertight compartment (12) is installed at the middle position of the support frame (11), and thrusters (13) are installed at four corners of the support frame (11) and are distributed at intervals along the circumference of the watertight compartment (12); wherein a high-definition camera and a core control unit are installed in the watertight compartment (12), the core control unit comprises a core controller and a communication module connected to the core controller, the core controller is also connected to the thruster (13), the core controller is connected to the high-definition camera via a switch, the core controller is connected to a host computer via a communication module, a PID controller is provided in the core controller, and a color recognition module is provided in the host computer.

2. An autonomous underwater robot according to claim 1, characterized in that: The watertight compartment (12) comprises a protective tube (121) and a protective cover (122) mounted on the protective tube (121) via a flange, a sealing ring is further provided between the protective tube (121) and the protective cover (122), the core control unit and the converter are both installed in the protective tube (121), a wiring board and a wiring box are further provided in the protective tube (121), and the high-definition camera is installed in the protective cover (122).

3. An autonomous underwater robot according to claim 1, characterized in that: The core control unit adopts an Arduino Mega 2560 core circuit board, and the core control unit can also be connected to a network expansion board, and the network expansion board adopts a W5100S network expansion board, and the network expansion board is also connected to the propeller (13).

4. A motion control method for an autonomous underwater robot, characterized in that: The method is based on the autonomous underwater robot (1) according to any one of claims 1 to 3, comprising the following steps: A control mode selected by a user is obtained, and the movement of the autonomous underwater robot (1) is controlled according to the control mode selected by the user, wherein the control mode includes a manual control mode and an automatic control mode.

5. The motion control method of an autonomous underwater robot according to claim 4, characterized in that: The method of controlling the movement of the autonomous underwater robot (1) using the manual control mode comprises: The user presses the "WASD" keys on the upper computer keyboard, and the upper computer sends the instructions corresponding to each key to the autonomous underwater robot (1), wherein the "WASD" keys on the keyboard correspond to controlling the autonomous underwater robot (1) to move forward, backward, turn left, and turn right; the user can also input the speed gear of the propeller (13) through the keyboard, and the upper computer sends the instructions corresponding to the speed gear to the autonomous underwater robot (1); After the core controller in the autonomous underwater robot (1) receives the key commands and speed gear position commands sent by the host computer through the communication module, it controls the four thrusters (13) according to the key commands and speed gear position commands, so that the autonomous underwater robot (1) moves forward, backward, turns left, and turns right at the speed gear position.

6. The motion control method of an autonomous underwater robot according to claim 5, characterized in that: The autonomous underwater robot (1) is controlled by the four thrusters (13) to perform forward and backward and turning movements; when the autonomous underwater robot (1) moves forward, thrusters 1 and 2 rotate forward, and thrusters 3 and 4 rotate reversely; when the autonomous underwater robot moves backward, thrusters 1 and 2 rotate reversely, and thrusters 3 and 4 rotate forward.

7. The motion control method of an autonomous underwater robot according to claim 6, characterized in that: The method of controlling the movement of the autonomous underwater robot (1) using the automatic control mode comprises: The host computer obtains an underwater video of a swimmer captured by a high-definition camera, extracts video frames from the underwater video for color detection through a color recognition module, determines the center position coordinates of the swimmer according to the color detection result, and sends the center position coordinates to the autonomous underwater robot (1); After the core controller in the autonomous underwater robot (1) receives the center position coordinates sent by the host computer through the communication module, the PID controller determines the speed and direction of each propeller (13) according to the center position coordinates, and controls the four propellers (13) according to the speed and direction of each propeller (13), so as to keep the swimmer always in the center position of the high-definition camera, thereby realizing real-time tracking and high-definition shooting of the swimmer.

8. The motion control method of an autonomous underwater robot according to claim 7, characterized in that: The color recognition module is the HSV color space of OpenCV. The video frame is extracted from the underwater video through the HSV color space of OpenCV to perform color detection, and the center position coordinates of the swimmer are determined according to the color detection result.

9. The motion control method of an autonomous underwater robot according to claim 8, characterized in that: The extracting of video frames from the underwater video for color detection using the HSV color space of OpenCV, and determining the center position coordinates of the swimmer according to the color detection result, include: Extracting video frames from a video of a swimmer underwater captured by a high-definition camera, and converting the video frames into an HSV color space, wherein the HSV color space is more suitable for color detection; By defining the HSV range of the target color, a mask is generated to isolate the specified color area, and after optimizing the mask quality using morphological operations, the boundary of the color area is determined by contour detection, and the noise area within the color area is filtered out; The centroid of each contour is calculated, and the center point of the main target is obtained by weighted average. The coordinates of the center point are converted into a new coordinate system with the center of the video frame as the origin, thereby obtaining the coordinates of the center position of the swimmer.

10. The motion control method of an autonomous underwater robot according to claim 7, characterized in that: The PID controller adopts a PID control algorithm to calculate the deviation between the current state of the autonomous underwater robot (1) and the target state, and adjust the control output according to the deviation, thereby achieving precise control of the dynamic characteristics of the autonomous underwater robot (1); wherein the PID control algorithm includes a proportional unit, an integral unit and a differential unit related to the deviation.

Images