389 results about "Tactile sensor" patented technology

The invention discloses a robot finger tactile perception method and system based on artificial intelligence, and the method comprises the following steps: S1, obtaining visual data and tactile perception initial parameters of a to-be-interacted object of a robot finger, carrying out the preprocessing of the visual data, and extracting the appearance features of the object, performing initial configuration on the touch sensing initial parameters; and S2, object recognition is conducted on the preprocessed visual data through a machine learning model, and the material category, morphological characteristics and surface attributes of an object are determined. According to the robot finger tactile perception method and system based on artificial intelligence, by combining a visual system and tactile sensor data and utilizing a convolutional neural network and Transform fusion architecture to extract local textures and global morphological features of an object, high-precision recognition of material categories, morphological features and surface attributes of the object is realized.

The invention discloses a bionic finger, a hand motion control device, a bionic hand control method and a robot, and belongs to the technical field of bionic robotics.The device comprises a plurality of flexible electric actuators which comprise electric actuating materials capable of actively deforming under excitation of an electric field; one end of the flexible electric actuator serves as a fixed end to be connected to the finger adaptation base, and the other end of the flexible electric actuator serves as a free end to be connected to the knuckle structure through a force transmission path. Wherein each flexible electric actuator can be independently controlled, and the plurality of flexible electric actuators cooperatively drive the knuckle structure to generate bionic motion; the passive constraint structure is configured to provide anisotropic mechanical constraint for active deformation of the flexible electric actuator, so that the active deformation is guided and converted into driving displacement or driving force in the first preset direction; and the guide structure is used for guiding the deformation direction of the flexible electric actuator. The device can integrate a strain sensor, an angle sensor and a touch sensor, and realizes closed-loop cooperative control through a controller.

The invention provides an isomorphic sensor dexterous hand-tactile glove system and a data acquisition method, and belongs to the technical field of tactile sensing, the system comprises a tactile data acquisition module which comprises a glove main body and a fixed flange arranged on the glove main body, a tactile sensor array is arranged on the palm side of the fixed flange and used for collecting tactile data of interaction between the glove body and an object; the visual perception module comprises an infrared camera array and an RGB (Red, Green and Blue) camera array, and is used for tracking marking balls arranged on the fixed flanges so as to solve pose data of the fixed flanges and collecting RGB images of interaction between the glove main body and an object; and the multi-modal data processing module is used for receiving the tactile data, the pose data and the RGB image, realizing space-time alignment of the data and generating a standardized data set. The system is simple in structure, rapid in deployment and high in acquisition safety, and can be suitable for tactile big data acquisition under multi-scene and multi-task conditions.

The utility model discloses a high-sensitivity flexible tactile sensor, a sensor module and an intelligent robot with a body, the high-sensitivity flexible tactile sensor comprises a flexible chamber substrate, an anti-corrosion protection ring, a flexible cover film, an induction material layer and a plurality of convex structures, the flexible chamber substrate comprises a flexible substrate, the anti-corrosion protection ring is arranged on the flexible substrate, and the anti-corrosion protection ring is arranged on the anti-corrosion protection ring. The electrode layer and the flexible bonding layer are sequentially and regularly arranged on the front face of the flexible substrate, the flexible bonding layer surrounds an interdigital electrode area of the electrode layer to form a cavity structure, and an electrode lead of the electrode layer is led out of the cavity structure. According to the high-sensitivity flexible tactile sensor, due to the innovative design of the flexible sealing cavity substrate, the flexible cover film and the protruding structure, the flexible tactile sensor shows high sensitivity and low detection limit.

The invention provides a visual tactile sensor, a geometric calibration method and computer equipment, and the visual tactile sensor comprises a base which is internally provided with an imaging unit; the light source module is arranged on the base and comprises 3N single-point light sources which are arranged around the imaging unit and can be independently controlled, and N is larger than or equal to 1; and the elastic housing is arranged on the base in a covering manner, and the imaging unit and the light source module are wrapped in the elastic housing. By constructing the novel curved surface visual tactile sensor and the matched geometric calibration method thereof, the problems that a traditional plane sensor is weak in multi-direction contact sensing capacity, difficult in curved surface calibration and the like are effectively solved, data generated by a physical model are used for training a lightweight neural network, and the accuracy of the curved surface visual tactile sensor is improved. Real-time surface normal prediction under single-frame three-color image input is realized, and the precision and reasoning speed of three-dimensional reconstruction are considered while hardware dependence and calibration cost are remarkably reduced.

A three-dimensional elastography method based on a vision-based tactile sensor. The method comprises several steps, which respectively involve: performing system construction and data processing, and acquiring contact deformation data collected by a vision-based tactile sensor; performing forward simulation; performing inverse optimization; calculating gradient information inside a target object, deriving the derivative of an objective function with respect to Young's modulus, calculating the partial derivative of a resultant force with respect to an elasticity distribution, and calculating the overall gradient of the objective function with respect to Young's modulus distribution; and outputting a Young's modulus distribution obtained by means of reconstruction and outputting a quantization reliability index. The method can realize accurate reconstruction of a Young's modulus distribution inside soft objects under robotic tactile sampling, and can output a corresponding reliability index, thus having high levels of practicability.

The invention relates to the technical field of element assembly, in particular to a mechanical arm control method for element assembly, electronic equipment and a medium. The method comprises the following steps: firstly, carrying out global scanning on an operation area through a visual sensor, and collecting first positioning information for assembling a male terminal and second positioning information for assembling a female terminal in real time; based on the first positioning information, a first dexterous hand of a first mechanical arm is controlled to grab the assembly male terminal, and the tail end pose of the assembly male terminal is estimated through a touch sensor array to obtain real-time pose data of the male terminal; based on the second positioning information, controlling the first dexterous hand to grab the assembly male terminal to move to an insertion preparation position; and based on the real-time pose data of the male terminal, the first dexterous hand is controlled to perform assembly insertion operation on the assembly male terminal, and the first dexterous hand is controlled to be separated from the assembly male terminal after a preset assembly achievement condition is met. In this way, robot target remote control actions adapting to diversified scenes can be achieved.

The invention relates to the technical field of aeronautical manufacturing and robot assembly, and discloses an aeronautical landing gear cable teleoperation collaborative assembly system and method, and the system comprises a master end interaction subsystem, a slave end assembly subsystem and a central control processing subsystem. The method comprises the following steps: acquiring multi-modal data through an environment monitoring camera, a six-dimensional force sensor and a touch sensor, and realizing space-time registration and state estimation by using Kalman filtering; and planning an optimal path by using a genetic algorithm based on the digital twinborn model and providing augmented reality guidance. And the system calculates visual confidence in real time, and adaptively switches a vision dominant control mode according to the visual confidence: when the vision is limited, the rigidity of the mechanical arm is automatically reduced, the force feedback weight is enhanced, and an operator is assisted to complete compliant operation in a blind area. According to the invention, the problems of sensing shielding and precise control of flexible cable assembly in a narrow cabin are solved, and the safety and efficiency of assembly operation are improved.

The invention discloses a coke residue characteristic detection method and system based on a visual tactile sensor, and the method comprises the steps: carrying out the contact scanning of a coke residue sample through the visual tactile sensor, and obtaining the surface three-dimensional topological point cloud data and distribution force vector data of the coke residue sample; carrying out regional or multi-angle scanning on the coke residue sample, and fusing and reconstructing surface three-dimensional topological point cloud data obtained by each scanning into a complete three-dimensional surface model; extracting a plurality of predefined feature parameters from the three-dimensional surface model and the distribution force data, and performing normalization processing to form a structured feature vector; and based on the structured feature vector, coke residue characteristic detection is carried out through a predefined discrimination rule or a machine learning model. According to the method, the visual tactile sensor is used for performing three-dimensional reconstruction and distribution force acquisition on the characteristics of the coke residue, the apparent description of manual visual inspection is converted into quantifiable three-dimensional shape parameters and characteristic indexes, and the problems that manual judgment is high in subjectivity and cannot be quantized and traced are solved.

The invention relates to the technical field of touch, in particular to an FBAR-based slip spectrum touch sensor, a sensor array and a preparation method. The tactile sensor comprises a thin film bulk acoustic resonator, the thin film bulk acoustic resonator comprises a substrate, a Bragg reflector, a lower electrode, a piezoelectric layer and an upper electrode, and the substrate, the Bragg reflector, the lower electrode, the piezoelectric layer and the upper electrode are sequentially stacked from bottom to top; moreover, the upper electrode is provided with a microstructure far away from the piezoelectric layer or close to the piezoelectric layer, and the microstructure is used for converting slippage into shear load. According to the designed tactile sensor structure, high-signal-noise output of the slip signal can be achieved, accurate slip detection can be achieved through the output slip spectrum, and meanwhile the friction state and material texture fingerprint output can be quantized.

The invention discloses a coplanar parallel capacitance-piezoelectric multi-mode tactile sensor and a preparation method thereof. The coplanar parallel capacitance-piezoelectric multi-mode tactile sensor comprises a substrate, a lower electrode, a middle functional layer, an upper electrode and a packaging protection layer which are sequentially arranged from bottom to top, the middle functional layer is a high-molecular polyvinylidene fluoride (PVDF) polymer film layer; the middle functional layer is divided into a capacitance functional area and a piezoelectric functional area which are coplanar and parallel, the piezoelectric functional area is located in the middle area of the polymer film layer, and the capacitance functional area surrounds the periphery of the piezoelectric functional area; the packaging protection layer is arranged at the top of the upper electrode; different functional areas of a capacitance functional area and a piezoelectric functional area are arranged on the same film layer surface, so that a capacitance dielectric film layer and a piezoelectric functional film layer are designed to be the same film layer, in combination with an in-situ plasma polarization process, directional high-voltage polarization processing is carried out on film surfaces of different areas of the same film layer, the overall thickness of the sensor after packaging can be effectively reduced, and the packaging cost is reduced. The sensor precision is improved.

The invention discloses a fruit conveying anti-blocking mechanism based on a neural network and a control method. The mechanism comprises a conveying channel, a disturbance disc connected with a motor through a universal joint, a touch sensing array and a gravity self-adaptive floating assembly. According to the mechanism, pressure data of a tactile sensing array on the surface of a disturbance disc are collected through Jetson, and the blockage state is judged in real time through a full-connection neural network; when blockage occurs, the Jetson directly controls the servo motor to change speed, the alternating inertia moment is matched with the gravity of fruits to overcome the resistance of the spring, and the disturbance disc is forced to passively incline around the center of the universal joint, so that the blockage is relieved. By means of the mode of combining motor rotating speed control and mechanical passive inclination, blockage caused by fruit accumulation is effectively damaged, and fruit damage is reduced while rapid dredging is achieved.

The application discloses a surface polishing quality evaluation method based on a flexible tactile sensor. In the application, the process of the quality evaluation method is that the flexible tactile sensor is connected at the end of a mechanical arm, so that the flexible tactile sensor is fully contacted with a polishing piece according to a polishing path, the flexible tactile sensor acquires parameters in the process of walking along the path, and after a series of algorithm processing, the surface quality of the polishing piece is represented, and the coordinate points with substandard quality evaluation values are processed again until the whole surface meets the requirements. The system can accurately position the polishing quality of the workpiece surface that does not meet the requirements and optimize the polishing, cooperates with the polishing, is important for improving the polishing quality and efficiency, and introduces a mechanical arm control cabinet to polish the workpiece again so that the calibration position area meets the process requirements, improves the precision and efficiency of traditional polishing surface quality monitoring, can be applied to the quality detection stage of the polishing process, and thus improves the process parameters of the workpiece, and thus improves the surface quality of the subsequent polishing workpiece.

The invention provides a hand multi-mode information sensing device and a robot humanoid skill learning method, and the device comprises a multi-mode touch sensor module which is used for sensing a hand multi-mode touch signal; the flexible strain sensor module is used for sensing a hand joint bending signal; the multi-modal motion capture module is used for sensing hand motion and posture signals, and the hand motion and posture signals comprise hand motion signals and / or hand posture signals; at least one of the hand multi-mode touch signals, the hand joint bending signals and the hand movement and posture signals forms hand multi-mode information representing gesture actions, hand movement and hand touch. According to the invention, sensing of hand multi-modal information in a hand operation process can be realized based on the hand multi-modal information sensing device, establishment of a sensing strategy and a control strategy is facilitated, cross-object and cross-task robust skill migration is realized, and self-adaptive operation capability and task success rate of a robot in an actual complex environment are remarkably improved.

This invention relates to the field of sensor technology and provides a tactile sensor. The tactile sensor includes a base layer, a first flexible circuit board layer, a second flexible circuit board layer, a first piezoresistive film layer, and a second piezoresistive film layer. The base layer has at least one first cantilever beam structure. The first flexible circuit board layer has at least one second cantilever beam structure corresponding to each of the at least one first cantilever beam structure and a first electrode formed on each second cantilever beam structure. The second flexible circuit board layer has at least one third cantilever beam structure corresponding to each of the at least one first cantilever beam structure and a second electrode formed on each third cantilever beam structure. At least one first piezoresistive film layer corresponds to at least one second cantilever beam structure, and at least one second piezoresistive film layer corresponds to at least one third cantilever beam structure. The tactile sensor of this invention can sense the magnitude and dynamic distribution of contact interaction forces, resulting in a good user experience.

The invention discloses a visual tactile sensor zero drift compensation method, device, equipment and program product. The method comprises the following steps: acquiring a tactile measurement value and an acceleration value of a visual tactile sensor; determining a zero drift error value of the visual tactile sensor according to the acceleration value and a preset zero drift detection model, and performing error compensation on the tactile measurement value according to the zero drift error value to obtain a tactile output value; or inputting the tactile measurement value and the acceleration value into a tactile perception model based on tactile input and acceleration joint optimization to obtain a tactile output value. According to the invention, zero drift compensation can be carried out on non-contact deformation of the elastic body caused by inertia force or direction-changing gravity, so that the measurement precision of the visual tactile sensor is improved, and the method can be applied to the technical field of sensors.

A system and method for an input device with a haptic sensor assembly are provided. The haptic sensor assembly includes a sensor subassembly with one or more touch sensor devices configured to provide force sensing responsive to pressure from an input object. The sensor subassembly also includes a flexible substrate configured to deform in response to the pressure from the input object. The haptic sensor assembly further includes a haptic subassembly with one or more haptic devices configured to provide haptic feedback in response to detecting the input object. The haptic subassembly also includes a bracket assembly comprising a first bracket portion and a second bracket portion. The one or more haptic devices are supported by the second bracket portion of the bracket assembly. The first bracket portion of the bracket assembly is disposed below the one or more touch sensor devices and configured to be coupled to a reference voltage.

A pose controller is provided for controlling a pose of an object to assemble with a mating object by a gripper of a robot arm. The pose controller includes an interface configured to receive tactile signals from the tactile sensors and transmit a control signal to the actuators, a processor, and a memory, in association with the processor, configured to store a precomputed set of tactile depth images and instructions of computer-implemented method. The instructions cause the processor to perform steps of computing measured tactile depth images from the received tactile signals, refining the pose of the object by matching between the precomputed set of tactile depth images and the measured tactile depth images by, generating a gripper trajectory command based on the refined pose of the object and a target pose of the object, and controlling the actuators of the robot arm according to the gripper trajectory.

The application discloses a flexible tactile sensing and feedback system and method based on texture recognition, which comprises an electrostatic flexible tactile sensor, a feedback actuator and a tactile feedback control circuit, the electrostatic flexible tactile sensor comprises a tactile interaction film for acquiring texture features and a pressure sensor for texture feature conversion; the feedback actuator completes tactile feedback of the texture feature signal acquired by the flexible sensor in the form of vibration; the tactile control system is mainly connected with the electrostatic flexible tactile sensor and the tactile feedback actuator through the feedback control circuit; the tactile feedback actuator has a stimulation reinforcement structure on the contact surface with the human body, which can further enhance the fine feedback of the tactile feeling. The application can effectively identify the texture features and complete the feedback of the fine tactile feeling in the form of vibration, provides effective assistance for the tactile recovery of the disabled, and has important application value in the game industry, especially in the development of virtual reality technology.

This invention relates to a high-density sensory mattress, comprising a mattress body, flexible tactile sensors, and a circuit. The mattress body has recessed grooves in which multiple flexible tactile sensors are disposed. The flexible tactile sensors are characterized by comprising an upper insulating layer, an upper electrode layer, a middle pressure-sensitive layer, a lower electrode layer, and a lower insulating layer. The middle pressure-sensitive layer is located between the upper and lower electrode layers. Both the upper and lower electrode layers consist of several evenly spaced linear electrodes. The circuit comprises a signal acquisition unit and a host computer. The signal acquisition unit uploads the acquired signals to the host computer via Bluetooth communication. This high-density sensory mattress can not only analyze the user's sleeping posture but also obtain the user's breathing and heartbeat signals through changes in pressure values, providing data support for assessing the user's sleep quality.

The utility model discloses a multi-core optical fiber integrated joint and a bearing bush temperature touch sensor detection device. The multi-core optical fiber integrated joint comprises a plurality of optical fiber joints, a multi-core joint and a locker, the multi-core joint is provided with a plurality of fourth through holes connected with the optical fiber joints, and the fourth through holes penetrate through the multi-core joint; an optical fiber ferrule is arranged in a first through hole of the optical fiber connector, the optical fiber ferrule is communicated with an optical fiber core optical path in a second through hole, and one end, far away from the second through hole, of the optical fiber ferrule extends out of a connector body of the optical fiber connector by a preset length; and the locking device is detachably connected with the connecting end of the multi-core joint and the optical fiber joint in a sealing manner. Accurate monitoring of the temperature of multiple feature positions of the generator bearing bush is achieved, a multi-core optical fiber integrated connector and a distributed temperature sensing network are organically combined, and a complete temperature field monitoring system is constructed by arranging special temperature sensors at key positions of the bearing bush.

This application belongs to the field of force detection technology and relates to a data acquisition structure for an array-type tactile sensor. The structure includes: a deformation layer and an array of permanent magnets; the array of permanent magnets is embedded in the deformation layer; wherein, along the x-direction, the number of permanent magnets is 0.1-0.5 times (s1 / d1); along the y-direction, the number of permanent magnets is 0.1-0.5 times (s2 / d1); along the x-direction, the distance between the outermost permanent magnet and the corresponding edge of the deformation layer is not less than 3*d1; along the y-direction, the distance between the outermost permanent magnet and the corresponding edge of the deformation layer is not less than 3*d1; along the z-direction, the distance between the permanent magnet and the corresponding upper surface of the deformation layer is not greater than 0.5*d1; 3mm ≤ the distance between adjacent permanent magnets in the x-direction ≤ 5mm; 3mm ≤ the distance between adjacent permanent magnets in the y-direction ≤ 5mm. This application also provides related tactile sensors and devices with tactile functions. The technical solution adopted in this application can improve the detection accuracy of tactile sensors.

The application discloses a passive dual-mode tactile sensor and a preparation method thereof, and belongs to the technical field of optical sensing and flexible tactile sensing. The sensor comprises a flexible support substrate, an elastic composite film containing long-afterglow light-emitting particles, micro-nano optical fibers embedded or attached to the surface of the elastic composite film, a flexible packaging layer, and an optical signal detection unit. When an external target approaches, the target surface reflects the scattered light, changes the output light intensity of the micro-nano optical fiber, and realizes non-contact sensing. When the external target contacts or presses, the composite film produces stress-induced luminescence enhancement and interface coupling change under the action of stress, and realizes contact force tactile sensing. The preparation method comprises light-emitting composite layer forming, micro-nano optical fiber taper preparation, interface coupling integration and packaging curing. The application has the advantages of no need for continuous light supply, compact structure, anti-electromagnetic interference, easy flexible integration, and suitability for human-computer interaction application.

The invention relates to the technical field of mechanical arms in the fields of industrial automation, intelligent storage and precision manufacturing, and discloses a novel four-degree-of-freedom mechanical arm which comprises a storage box. The telescopic arm is arranged on one side of the storage box and can realize limiting telescopic adjustment; the clamping mechanism is arranged at one end of the telescopic arm and is used for clamping an object; the novel four-degree-of-freedom mechanical arm has the remarkable advantages that the nested telescopic arm is matched with a built-in drag chain, so that the section size is greatly reduced, the novel four-degree-of-freedom mechanical arm is adaptive to compact space operation, and the compactness is optimized; the drag chain is integrated with a cable, winding and pulling are avoided, and stable power supply and signal transmission are guaranteed; three motors independently drive posture adjustment, power transmission is efficient, response is fast, precision is high, and the precision operation requirement is met; and a tactile sensor of the clamping mechanism realizes self-adaptive pressure control, so that damage to the article or infirm clamping is avoided, and the adaptive range is widened.

A control method for a support robot, the method comprising: in response to recognizing that a target object has an intent to require support, controlling a support robot to move toward the target object, and when the support robot moves to a target movement position, controlling a robot arm to move to a target joint position, wherein the target movement position and the target joint position are both determined on the basis of the relative position between the target object and a target sensor; and in the process of the robot arm moving to the target joint position or after the robot arm moves to the target joint position, when it is detected by means of a tactile sensor that an external force is applied to the robot arm, performing compliance control on the support robot. Further provided are a support robot, an electronic device, a computer storage medium, and a computer program.

The embodiment of the present application provides a touch panel and a driving method thereof and a touch device, the touch panel comprising: a substrate, and a touch structure and a tactile sensor which are arranged in a stack on the substrate; the touch structure comprises a first electrode layer, an insulating layer and a second electrode layer which are arranged in a stack on the substrate; the tactile sensor comprises a third electrode layer, a piezoelectric layer and a fourth electrode layer which are arranged in a stack on the substrate; wherein at least one electrode layer in the touch structure and the tactile sensor is multiplexed with each other. The above touch panel provided by the embodiment of the present application adopts the structure of integrating the tactile sensor and the touch structure, can realize the touch function and the tactile reproduction function, and at least one electrode layer in the tactile sensor and the touch structure is multiplexed with each other, so that the manufacturing of at least one electrode layer can be saved, the manufacturing process flow can be simplified, the module thickness can be reduced, the production cost can be saved, and the production efficiency can be improved.

The utility model relates to a sensing electrode arrangement structure on a single-layer plate and a tactile sensor, the single-layer plate is provided with a sensing area, and a plurality of electrodes for implementing capacitance and / or piezoelectric sensing are arranged in the unit area of at most one square centimeter in the sensing area; the electrodes are strip-shaped electrodes, the strip-shaped electrodes have the same shape and size, the central positions of the strip-shaped electrodes are uniformly distributed, and the ratio of the width to the length of each strip-shaped electrode is configured to be 1: 2.9-3.2; and each strip-shaped electrode leads out a wire for transmitting electric signals to the outside on the single-layer plate.

The invention discloses a visual tactile sensor zero drift self-correction method, device, equipment and product, and the method comprises the steps: obtaining a preset visual tactile data set, carrying out the camera noise data enhancement and illumination jitter data enhancement of the visual tactile data set based on a camera noise model and RGB channel adjustment, and obtaining a training data set; training according to the training data set to obtain a visual tactile resolving model after zero drift correction; acquiring a real-time camera image of the visual tactile sensor, and determining a real-time difference image according to the real-time camera image and a no-load camera image of the visual tactile sensor; inputting the real-time difference image into a visual tactile calculation model to obtain a tactile output value; wherein the no-load camera image is updated according to a preset time interval. According to the invention, zero drift correction of random change and trend change is realized, so that the accuracy and reliability of the visual tactile sensor are improved, and the method can be applied to the technical field of sensors.

The application provides a kind of adaptive human-computer interaction method and system based on multi-modal perception, it is related to human-computer interaction technical field, acquires the multi-modal original perception information flow that user obtains in mixed reality space through depth vision, bone conduction and flexible tactile sensor, respectively to its penetration depth calculation, voiceless speech decoding and mechanical response matching processing are handled, obtain interactive penetration depth sequence, internal speech instruction coding sequence and virtual tactile feedback expected intensity sequence.Multiple modal intention conflict detector detects cross-modal intention conflict, generates intention conflict representation vector, finally generates interactive mode smooth switching instruction according to the intention conflict representation vector, triggers mixed reality space interaction paradigm conversion, realizes the adaptive conversion of interaction paradigm in mixed reality space, effectively solves the problem of multi-modal interaction intention conflict processing difficulty in traditional method, greatly improves the accuracy, fluency and naturalness of human-computer interaction.