3168 results about "Underwater robot" patented technology

The invention relates to a mini-size underwater observing robot, which comprises an underwater robot body and an above-water control box, wherein, two sides of an electronic cabin on the underwater robot body are horizontally provided with a left propeller, a right propeller and a lamp; a middle part on the electronic cabin is vertically provided with a vertical propeller; a bracket and a manipulator are arranged together with a lower part of the electronic cabin, the interior of which is provided with a compass, a temperature gauge, a depth gauge and a control circuit board; a front part on the electronic cabin is provided with a camera with variable focus, a camera pan and tilt and a lamp; a back part on the electronic cabin is provided with a camera with fixed focus; video images are transferred to a display on the above-water control box through shielded cable; the above-water control box consists of a control panel, a control circuit, a liquid crystal display and a chassis body. The invention transfers the shapes and the movement state of observed objects under water to the above-water control box through a video sensor, so the repair personnel can analyze the images; besides, the arranged manipulator can carry out grabbing work with light weight.

The invention relates to a microminiature operation underwater robot of a nuclear power plant, and the robot comprises an underwater robot body and an onshore control system, wherein two propellers are respectively arranged in the horizontal and vertical directions of the robot body, a depth gauge is arranged on the right side of the front part of the robot body, a manipulator is arranged at the bottom in front of the robot body, and a sonar is arranged on the top of the robot body; a control cabin is arranged in the middle rear part of the robot body; an outer cabin is sealed by a transparent glass cover, and is provided with a rearview camera and an auxiliary lighting light-emitting diode (LED) lamp; a front-view camera system is arranged at the front part of the robot body, and comprises a zooming radiation resistant camera tube, a tripod head and a lighting lamp; a video image and control signal is transmitted to the onshore control system through a shield cable; and the control system comprises a movement control rod, a manipulator control button, a keyboard, a main display screen and a speed governing knob. The microminiature operation underwater robot of the nuclear power plant is used for the monitoring and the simple foreign body fishing of a core pool, a spent fuel pool and a component pool of the nuclear power plant.

The invention discloses an underwater pipeline detection and tracking system and detection method of an automatic remote control underwater robot. The underwater pipeline detection and tracking system comprises a lower computer and an upper computer. The lower computer is arranged underwater, and the upper computer is arranged on a water surface mother ship. The lower computer comprises a sensor module, an optical visual module, an embedded controller and an underwater optical transceiver. The sensor module and the optical visual module are connected with the signal input end of the embedded controller respectively. The signal output end of the embedded controller is connected with the signal input end of the underwater optical transceiver. The upper computer comprises an overwater optical transceiver, a water surface monitoring module and a manual operator. The manual operator is in circuit connection with the water surface monitoring module which is in circuit connection with the overwater optical transceiver. The underwater optical transceiver is connected with the overwater optical transceiver through optical fibers. The automatic remote control underwater robot can transmit images in real time, the water surface mother ship can monitor the underwater environment in real time, safety of the complex underwater operation condition is guaranteed, and detection and tracking tasks of an underwater pipeline are finished.

The invention provides an underwater robot platform. The underwater robot platform comprises at least one underwater robot, a monitor terminal, a buoy communication system and a water sampling device. The monitor terminal is used for sending motion and task instructions to all underwater robots; the buoy communication system is connected with the underwater robots through CAN cables to receive the motion and task instructions through the CAN cables, and the buoy communication system moves under dragging of the underwater robots and obtains positioning information and communication information of the underwater robots; the water sampling device communicates with the underwater robots through standardized interfaces and is used for collecting and recording water sample information; the underwater robots are used for completing corresponding motion and tasks according to the received motion and task instructions. The propulsion mode combining CPG bionic propulsion and gliding propulsion is adopted, the multiple underwater robots are cooperatively controlled through a wireless sensor network technology, and the underwater robot platform is high in real-time performance, movability and efficiency and has the long-time cruising ability.

The invention discloses a reinforcement learning-based AUV behavior planning and motion control method, which belongs to the technical field of underwater robots and aims at solving the problems of limited training experience and difficult application in a real environment as complex task planning by the AUV depends much on manual experience and a control method designed based on an intelligent algorithm needs an accurate environment mode. AUV tunnel detection is defined as a general task; behaviors corresponding to task completion comprise target trending, wall tracking and obstacle avoidance; a control instruction generated by the robot under water to complete the planned behavior is defined as an action; and when the AUV executes a tunnel detection task, a deep reinforcement learning DQN algorithm is used for real-time behavior planning, a corresponding deep learning behavior network is constructed, and planning of the tunnel detection task is completed. The AUV action network is trained by the DDPG method, the AUV is regarded as an environment model, and force-to-state mapping is obtained, thereby realizing the action control of the AUV.

The invention belongs to the technical field of underwater robots, in particular to a long-term fixed-point vertical-section observation-type underwater robot. The long-term fixed-point vertical-section observation-type underwater robot comprises a propulsion section, a stern buoyancy adjusting section, a battery cabin section, an electronic cabin section, a bow buoyancy adjusting section and an observation load section, wherein the propulsion section and the observation load section use open frame structures; the observation load section carries an oceanographic hydrological data observation sensing equipment; the upper part of the propulsion section is provided with a satellite antenna; the stern buoyancy adjusting section, the battery cabin section, the electronic cabin section and the bow buoyancy adjusting section are arranged in a full-sealed pressure resistant cabin; and through double-way buoyancy adjusting of the stern buoyancy adjusting section and the bow buoyancy adjusting section, the motion posture of the underwater robot is adjusted and the underwater robot can hover at a fixed point. The underwater robot realizes a high-accuracy repeatable double-way buoyancy adjusting function and can realize autonomous balancing and fixed-point hovering.

The invention provides an underwater robot adjusted through three oil pockets, and a depth-setting control method thereof. The method comprises the following steps: information, such as depth, longitudinal velocity and attitude angle, etc., is obtained through corresponding sensors; the static submergence or dynamic submergence is determined according to a host computer instruction; if the instruction indicates the static submergence, a bow, a midship and a stern respectively pump oil from the oil pockets at the same time, therefore, the displacement volumes of the oil pockets are reduced, the buoyancy force of the underwater robot is smaller than the gravity force in general, and the underwater robot sinks; if the instruction indicates the dynamic submergence, an axial main thruster is started, and enters a constant speed motion state with acceleration, an oil storage tank at the bow part sucks oil from the bow oil pocket, and therefore, the displacement volumes of the bow oil pocket is reduced; since the oil is discharged to the stern oil pocket from an oil storage tank at the stern part, the displacement volume of the bow oil pocket is increased; the underwater robot is changed into a state of trim by head from zero pitch, and bow trim occurs; the bow trim motion is coupled by the axial motion at the moment, and longitudinal trim submergence is realized; and the oil suction action and the oil discharge action are opposite when the static floating or dynamic floating occurs. The method has significance for the long-distance voyage underwater robot regarding to energy conservation.

The invention relates to an underwater target positioning method. The underwater target positioning method includes that (1) a recognition system is provided and comprises a buoy subsystem, a sonar subsystem, a target recognition subsystem and a control subsystem, the buoy subsystem floats on a water surface above an underwater robot, the target recognition subsystem, the sonar subsystem and the control subsystem are disposed on the underwater robot, the buoy subsystem is used for determining global positioning system (GPS) position of a buoy, the sonar subsystem is used for determining a buoy relative position between the buoy and the underwater robot, the target recognition subsystem is used for determining the type of an underwater target and for determining a target relative distance between the underwater target and the underwater robot, and the control subsystem determines the GPS position of the underwater robot and the GPS position of the underwater target according to the buoy GPS position, the buoy relative position and the target relative distance; (2) positioning is performed by means of the recognition system. By means of the underwater target positioning method, GPS positions of the underwater robot and the underwater target can be accurately determined, and meanwhile, the type of the underwater target can be recognized.

The invention relates to an automatic obstacle avoidance method for intelligent underwater robots, in particular to a method for considering underwater robot moving objects and obstacles and underwater robot control performances integrally to achieve obstacle avoidance. The method comprises performing global path planning according to job tasks and chart database information; reading underwater robot motion sensor information and obstacle avoidance sonar information; calculating underwater robot safety alerting distances, and establishing a safe virtual outer casing of an underwater robot; determining whether obstacle avoidance is needed; and determining whether an object is reached, and the task is completed if the object is reached. According to the automatic obstacle avoidance method, effects of speed information of underwater robots are introduced in robot obstacle avoidance strategies, local obstacle avoidance planning and control and hydrodynamic performances of underwater robots are combined, established obstacle avoidance strategies can reflect dynamic obstacle avoidance capacities of underwater robots, and underwater robot survival capabilities are improved.

A modular system for building underwater robotic vehicles (URVs), including a pressure vessel system, modular chassis elements, a propulsion system and compatible buoyancy modules. The pressure vessel system uses standardized, interchangeable modules to allow for ease of modification of the URV and accommodation of different internal and external components such as sensors and computer systems. The system also includes standard, reconfigurable connections of the pressure vessel to the modular chassis system. A standardized, modular propulsion system includes a magnetic clutch, and a magnetic sleeve used to power the URV on or off.

The invention relates to a multi-underwater-robot collaborative control system, comprising a control system, an image acquisition equipment, a plurality of underwater robots and a power supply; the control system comprises a master control device and a wireless communication equipment; the master control device comprises a computer, a real-time display equipment and an operating equipment; the master control device keeps communication with each underwater robot through the wireless communication equipment; an image processing module, a collaborative control module and a user interface module are arranged in the computer; a robot control module is arranged in each underwater robot; each robot control module receives an instruction from the computer and sends the instruction to the corresponding underwater robot, and feedbacks the internal state information of the underwater robot to the computer at the same time. The multi-underwater-robot collaborative control system is provided with strong universality and scalability and has a graphical user interface; and the system also can simulate the dynamic process and has the recording and playback functions.

The invention discloses an inner system for controlling the gestures of an underwater robot, comprising a main controller connected with an adjustment mechanism, a gesture sensor, and an upper computer controller, wherein the adjustment mechanism is a balance adjustment mechanism arranged inside the underwater robot, and comprises a gravity slider, a double-shaft drive motor, a worm, a guiderail, a slide bar, a limit switch and a mechanism platform; the double-shaft drive motor is connected with the worm to drive the worm to rotate bidirectionally; the worm drives the slide bar to perform planar movement through the transmission of a lead screw; one end of the slide bar is connected with the lead screw of the worm and penetrates the gravity slider, while the other end thereof is connected with the guiderail by a slider and drives the gravity slider to move in a plane so as to realize the gravity adjustment of the underwater robot and control the transverse swing and longitudinal incline gestures of the underwater robot. The control system for gestures can be widely applied to the gesture control of the underwater robot.

The invention discloses a real-time navigation system and a real-time navigation method for an underwater structure detection robot. The navigation system comprises a magnetic compass, a gyroscope, an accelerometer, a depth meter and a navigation microprocessor, wherein the magnetic compass, the gyroscope, the accelerometer and the depth meter are used for respectively collecting magnetic field intensity, an angular speed, a linear speed and submerged depth data and transmitting the magnetic field intensity, the angular speed, the linear speed and the submerged depth data to the navigation microprocessor; the navigation microprocessor is used for calculating attitude and position of the underwater robot according to the collected data. The navigation method comprises an attitude algorithm, a speed algorithm and a depth algorithm; according to the attitude algorithm, a complementary filtering method, a quaternion gradient descent method and a Kalman algorithm are combined for obtaining an attitude matrix and an attitude angle; the speed algorithm is used for calculating the speed and the position of the robot by using a three-order upwind scheme with rotary compensation; the depth algorithm is used for processing the data of the depth meter by using a moving average filter algorithm so as to obtain the submerged depth. By virtue of the real-time navigation system for the underwater structure detection robot and the method thereof, the navigation cost is reduced and a relatively good navigation precision is achieved.

The invention relates to a multi-underwater robot semi-physical simulation system and a control method thereof. The system comprises a visual scene display computer, a virtual environment computer, an electric switching device and an airborne autopilot. The visual scene display computer is in network communication connection with the virtual environment computer; kinematics models and dynamics models of each robot are stored in the virtual environment computer, and various kinds of virtual sensor device information is generated through model computation; the electric switching device switchesa standard cable interface of an expansion card of the virtual environment computer to be an interface capable of conveniently connecting the multi-underwater robot airborne autopilot; the airborne autopilot is a real underwater robot soft hardware control system, and is used for generating the executor control quantity according to own motion planning and closed loop, transmitting the executor control quantity to the virtual environment computer through the electric switching device and transmitting cooperation information to other robots through the virtual environment computer according tomission requirements. The multi-underwater robot semi-physical simulation system and the control method thereof are convenient to expand sensors and device nodes, and the system is excellent in expandability, high in transportability and convenient to configure various kinds of underwater robots.

The invention relates to launching and recycling technologies for underwater gliders or other underwater or water surface vehicles, in particular to an intelligent underwater robot shipborne launching and offshore recycling mechanism and corresponding method. The recycling mechanism comprises a shipborne body, a main recycling slide way, an auxiliary recycling slide way, an electric turning mechanism, an electric control cabinet, a tensioning mechanism, a multi-sensor fusion positioning system, a dragging unit and a hook system. The recycling mechanism is simple, reasonable, reliable in structure, and easy and convenient to operate, the underwater gliders, autonomous underwater vehicles (AUV), other underwater robots and the like can be launched and recycled quickly and efficiently, the workload of sailors and related staff on a ship are greatly relieved, the dangerous factors in the launching and recycling processes of the underwater robots are avoided, and the problem that the launching and recycling processes waste time and labor is solved.

The invention discloses a combined navigation method of an integrated sonar micro navigation autonomous underwater robot, mainly comprising the following steps of: (1) acquiring initial absolute position information of the autonomous underwater robot by using a global positioning system, acquiring speed information and posture information of the autonomous underwater robot by using a sensor and estimating the speed information and/or posture information of the autonomous underwater robot by using a sonar system; and (2) fusing the speed information and the posture information which are acquired by the sensor and the speed information and/or posture information estimated by the sonar system by using a data fuse method and acquiring absolute position information and posture information of the autonomous underwater robot by combing the initial absolute position information of the autonomous underwater robot. The invention has the advantages that the absolute position of an AUV (Autonomous Underwater Vehicle) can be estimated and the navigation precision of the AUV can be improved by fusing the speed and/or posture information estimated by AUV-boarded sonar and the speed and posture information acquired by the sensor.

The invention provides an underwater autonomous robot fixed depth control method based on reinforcement learning and belongs to the underwater robot control field. The method comprises steps that firstly, a Markoff decision process model for underwater autonomous robot fixed depth control is constructed, and expressions of a state variable, a control variable, a transfer model and a one-step lossfunction for underwater autonomous robot fixed depth control are respectively acquired; the decision network and the evaluation network are respectively established; through reinforcement learning, the decision network and the evaluation network can be continuously updated whenever an underwater autonomous robot moves forwards for each step during fixed depth control training till convergence; thefinal decision network for fixed depth control is acquired. The method is advantaged in that fixed depth control on the underwater autonomous robot under the condition of a completely-unknown underwater autonomous robot dynamic model is realized, and the practical value is high.

The invention belongs to the field of recovery of underwater robots, and particularly relates to a draft gear for recovering the underwater robot. The draft gear comprises a hydraulic winch, a box body, a rotary straight girder, a rotating mechanism, a pitching hydraulic cylinder, a stretching hydraulic cylinder and a draft arm with three degrees of freedom, namely a rotating degree of freedom, a pitching degree of freedom and a stretching degree of freedom, wherein the box body is disposed on a mother ship, the hydraulic winch is arranged in the box body, and a traction rope connected with the underwater robot is connected with the hydraulic winch through the draft arm; one end of the rotary straight girder is connected with the rotating mechanism disposed on the box body, the other end of the rotary straight girder is hinged with the draft arm, the stretching hydraulic cylinder is arranged on the draft arm and drives the draft arm to stretch, the pitching hydraulic cylinder is arranged on the rotary straight girder, and an output end of the pitching hydraulic cylinder is hinged with the draft arm; and a hydraulic station is arranged in the box body and is used for supplying power to the hydraulic winch, the rotating mechanism, the pitching hydraulic cylinder and the stretching hydraulic cylinder. The draft gear disclosed by the invention has the advantages of simple and reliable structure, complete functions, easiness to operate and the like.

The present invention relates to a marmem wire driven pectoral fin wave propulsion bionic underwater robot. It includes self-body and pectoral fin. The described pectoral fin includes at least four pectoral fin wave joints connected with self-body, between every adjacent two pectoral fin wave joints a fin film is connected. The described pectoral fin wave joint is formed from elastic body, marmem wire, skin and matrix. Said invention is simple in structure and is high in working efficiency.

The present invention discloses a method and system for controlling an underwater robot locus based on deep reinforcement learning. The system comprises a learning phase and an application phase. In the learning phase, a simulator simulates the running process of an underwater robot and collects the data of the simulated running underwater robot, the data comprises the state of each moment and the target state of the next moment corresponding to each moment, and the learning is performed aiming at a decision neural network, an auxiliary decision neural network, an evaluation neural network and an auxiliary evaluation neural network through the data. In the application phase, the state o the underwater robot at the current moment and the target state of the underwater robot at the next moment are obtained and input to the decision neural network obtained through the final learning in the learning phase, and the decision neural network is configured to calculate the propulsive force required by the underwater robot at the current moment. The method and system for controlling underwater robot locus based on the deep reinforcement learning can realize accurate control of the underwater motion track.