Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

192 results about "Sonar sensor" patented technology

Sonar (ultrasonic) sensors allow Rover to detect obstacles and avoid them. Sonar sensors can be more sensitive than IR sensors, making them the preferred option for obstacle avoidance. Normally, a single sonar sensor is used, at the front of the rover.

Robot indoor positioning and navigation method based on single vision

The invention discloses a robot indoor positioning and navigation method based on single vision. The robot indoor positioning and navigation method specifically comprises the following steps of S1, for first-time use, creating an indoor map of a room by the following specific steps of (A), setting three identifiable marking points at the indoor roof, enabling a robot to use an indoor charging point as an original point to create an indoor coordinate system, calibrating the information of coordinates and directions of the three marking points, and calibrating the direction of an electronic compass; (B) establishing a right-angle coordinate system of a camera; (C) controlling the robot to move in the room, detecting the edge of the room via a sonar sensor, and generating the indoor map of the room; S2: for indoor positioning, when the robot is set at any point of the room, enabling a single-eye camera to measure the three marking points, and combining with the right-angle coordinate system of the camera and the indoor coordinate system to calculate the data of positions and directions of the robot; for autonomous navigation: setting a target point of the robot as M2, and enabling the robot to perform the autonomous navigation via the indoor positioning and target point positioning.
Owner:塔米智能科技(北京)有限公司

Novel ferroelectric single-crystal lead ytterbium niobate-lead magnesium niobate-lead titanate

The invention relates to the growth, the structures and the properties of novel ferroelectric single-crystal lead ytterbium niobate-lead magnesium niobate-lead titanate. The crystal belongs to a perovskite structure, has an MPB region and has a chemical formula of (1-x-y)Pb(Yb1 / 2Nb1 / 2)O3-xPb(Mg1 / 3Nb2 / 3)O3-yPbTiO3 which is short for PYMNT or PYN-PMN-PT. By adopting a top crystal-seeded method, the crystal with large size and high quality can grow under the conditions that the growth temperature of the crystal is 950-1100 DEG C, the crystal rotation speed is 5-30rpm, and the cooling speed is 0.2-5 DEG C / day, and the grown crystal exposes a 001 natural growth surface. Through X-ray powder diffraction, the system is confirmed as the perovskite structure; and through ferroelectric, dielectric and piezoelectric measurement, the ferroelectricity, the dielectric property and the piezoelectricity of the crystal are analyzed. The crystal has high Curie temperature and trigonal-tetragonal phase transition temperature, large piezoelectric constant and electromechanical coupling factor, high dielectric constant and low dielectric loss and better heat stability. The crystal can be widely applied to devices in the piezoelectric fields of ultrasonically medical imaging, sonar probes, actuators, ultrasonic motors, and the like.
Owner:FUJIAN INST OF RES ON THE STRUCTURE OF MATTER CHINESE ACAD OF SCI

Monitoring method and monitoring system for detecting grinding machine processing status

InactiveCN102275131AMonitor the whole process of processingReal-timeGrinding feed controlSignal onEmbedded system
A monitoring method and a monitoring system for detecting a processing state of a grinding machine are disclosed. A sonar sensor is employed to receive a sonar signal which is sent by a numerical control grinding machine during the processing of a work piece, and then to convert the sonar signal into an electric signal; an acoustic emission detection system is employed to convert the detected electric signal which is output by the sonar sensor into an RS232 communication protocol signal and a PROFIBUS communication protocol signal, respectively; the RS232 communication protocol signal is transmitted to a numerical control system on the grinding machine, and then the numerical control system displays the received RS232 protocol signal on a screen in the form of dynamic waveform, thereby realizing visualization of the grinding process; and the PROFIBUS communication protocol signal is transmitted to a PLC (Programmable Logic Control) system for PLC logic programming, and a collision signal and a contact signal of the grinding machine and the work piece which are output by the PLC system are transmitted to the part program of the numerical control system, thereby realizing collision prevention and idle running elimination. The monitoring method and the monitoring system of the invention are capable of monitoring the whole processing of the numerical control grinding machine, so that the grinding process can be optimized; and the grinding quality and efficiency are improved.
Owner:SHANGHAI SANY PRECISION MACHINERY

Underwater target identification method based on semi-tensor product neural network

The invention provides an underwater target identification method based on a semi-tensor product neural network, and the method comprises the steps: receiving an underwater sound signal through an underwater sonar sensor, and enabling the time domain and frequency domain information of the sound signal to be presented in a LOFAR map through short-time Fourier transform; constructing a data sample semi-tensor product neural network by taking a LOFAR map sample as an input characteristic matrix; dividing the received underwater acoustic signals into a training set and a verification set, and inputting the training set and the verification set into a semi-tensor product neural network for training and verification; selecting different hyper-parameters, carrying out model training on a semi-tensor product neural network by using a training set, comparing test effects of a verification set, and determining hyper-parameters with high test accuracy; and finally inputting the currently acquired sound signal of the underwater target into the trained semi-tensor product neural network after model, and giving a judgment result. The underwater target recognition rate can be improved, the application scene is expanded, and the method is suitable for recognizing the underwater target in complex marine environment noise.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Measurement system and method for detecting orientation and size of underwater target on basis of laser sound source

The invention discloses a measurement system and method for detecting the orientation and the size of an underwater target on the basis of a laser sound source. According to the measurement system and method, the sound source is generated through lasers, laser energy is converted into sound wave energy, an acousto-optical coupling interference type optical fiber hydrophone array serves as a receiving sensor, the defects that in the optical measurement process, optical waves which are used are large in attenuation and the measuring distance is short are overcome, the defects of a sonar sensor in traditional acoustics detection are overcome, and the advantages that mobility and flexibility are high are achieved. Meanwhile, a sound source signal is generated through a laser-induced sound system, and generated sound signals have the advantages of being high in sound pressure level, wide in frequency spectrum, capable of conducting non-contact type control, and the like. An acousto-optical coupling interference type optical fiber hydrophone is used as the acoustic signal sensor, and the acoustic signal sensor has the advantages of being capable of detecting underwater acoustic signals in the non-contact mode, high in mobility, small in size, flexible in structural design, and the like.
Owner:ZHEJIANG UNIV

Magnetostrictive metal substrate-based magnetic sonar sensor and preparation method thereof

The invention discloses a magnetostrictive metal substrate-based magnetic sonar sensor, and belongs to the technical field of magnetic acoustic detection. The magnetostrictive metal substrate-based magnetic sonar sensor comprises a magnetic field detection part composed of two magnetic acoustic surface wave resonator units and an acoustic pressure detection part composed of 2xN arrayed piezoelectric ultrasonic transducer units; the magnetic acoustic surface wave resonator units and the piezoelectric ultrasonic transducer units share magnetostrictive substrates, metal buffer layers, piezoelectric thin films and protective layers; and the thicknesses of the piezoelectric thin films in the two magnetic acoustic surface wave resonator units are different. The magnetostrictive metal substrate-based magnetic sonar sensor integrates magnetic acoustic surface wave resonators and piezoelectric ultrasonic transducers to realize magnetic field detection and acoustic pressure detection of an underground target such as a ship, a submarine and a UUV (Unmanned Underwater Vehicle), and has the advantages of simple structure, easiness in machining, low cost, high integration degree, high detectionsensitivity, low loss, high response speed and the like.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Deep-reinforcement-learning-based indoor robot scene active recognition method

ActiveCN107688856ALower requirementImprove the accuracy of scene recognitionNeural learning methodsLearning machineTraining phase
The invention provides a deep-reinforcement-learning-based indoor robot scene active recognition method, and belongs to field of machine learning and the technical field of robots. The method comprises the steps that a classification neural network NL capable of recognizing sonar information binaryzation contour figure ring projecting vectors is trained; a reinforcement learning training phase isentered, wherein scene recognition testing is conducted on a robot in a scene multiple times, and in the testing process, a reinforcement learning neural network NQ is trained and subjected to fittingto obtain a function approximator; when reinforcement learning neural network NQ finishes training, an execution phase is entered, wherein the robot indoor scene active recognition function is testedaccording to scene contour information collected by a sonar sensor. According to the method, on the basis of an extreme learning machine algorithm, the calculation efficiency is improved; on the basis of a reinforcement learning algorithm, the scene recognition accuracy rate is increased. The method can adapt to different scene recognition tasks, people does not need to be involved, the robot learns actively, and the scene recognition accuracy rate is increased automatically.
Owner:TSINGHUA UNIV

AUV target searching method

The invention discloses an AUV (Autonomous Underwater Vehicle) target searching method. The AUV target searching method comprises the steps of establishing a sonar detection model, establishing an environment sensing map and searching a target based on an improved attraction source. According to the invention, surrounding environment information is detected in real time through the sonar sensor inan unknown underwater environment without prior information; various environment sensing maps are created and updated; a pheromone release mechanism is improved; therefore, the AUV can perform returnvisit on the area with lower target existence probability under the condition of higher coverage rate of the search area; the target omission caused by the detection probability problem is avoided; the AUV is prevented from repeatedly searching in the searched area; according to the method, to-be-activated attraction sources are arranged at opposite corners of a search area, targets at corners can be searched more easily by activating the to-be-activated attraction sources, updating formulas and search income functions of all environment perception maps are formulated, an AUV is made to makea maximum income movement decision, and the search efficiency is improved while the search reliability and stability are guaranteed.
Owner:HARBIN ENG UNIV

Sensor fusion and improved Q learning algorithm based dynamic barrier avoidance method

ActiveCN109445440AIncrease the angle of motionMake up for the shortcomings of detectionNavigational calculation instrumentsPosition/course control in two dimensionsAlgorithmSimulation
The invention relates to a sensor fusion and improved Q learning algorithm based dynamic barrier avoidance method. The method comprises the steps that S1) the safe distance to a barrier and target coordinate position information and scope during movement of a robot are set; S2) a present pose of the robot is determined, a navigation path is planned, and forwarding is started; S3) in the navigationprocess, environment data detected by a sonar sensor and environment data detected by a laser sensor are preprocessed and characterized and then fused to obtain environment data; S4) whether dynamicbarrier avoidance is needed for the present robot state is determined according to the fused environment data, if YES, a step S5) is carried out, and otherwise, a step S6) is carried out; S5) an improved Q learning dynamic barrier avoidance method is used to obtain the next motion state (a, theta); and S6) whether the robot reaches a target point is determined, if NO, the step S2) is returned to continue navigation, and otherwise, navigation is ended. The method can be used to overcome defects of the single sensor effectively, and improve the barrier avoidance efficiency in the dynamic environment.
Owner:CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products