306 results about "Haptic sensing" patented technology

The invention provides an intelligent grabbing control method and system based on tactile perception, and the method comprises the steps: obtaining a tactile feedback signal through a sensor array of a humanoid robot, carrying out the frequency domain decomposition of the signal through a Fourier transform method, and carrying out the analysis of the pressure and deformation data of each contact point on the surface of a to-be-grabbed object, calculating to obtain frequency characteristic distribution of the tactile feedback signal; if the initial estimation value of the object rigidity gradient exceeds a threshold value, performing finite element analysis on the object rigidity gradient, and combining a time domain processing result of the tactile feedback signal to obtain object rigidity gradient distribution; carrying out probability modeling on the deformation field by adopting a Bayesian inference method according to the gradient distribution of the rigidity of the object, and carrying out iterative optimization on a modeling result to obtain dynamic update parameters mapped by the deformation field; and regenerating an action sequence of the end effector of the humanoid robot based on the optimized strategy according to a trigger condition of grabbing failure detection, and determining a final grabbing control parameter.

The invention discloses a manipulator grabbing control system based on visual identification, and the system comprises a visual identification module which is used for collecting the three-dimensional form data and surface feature information of a target object, and eliminating the noise interference in an original image through preprocessing; the multi-modal fusion processor is used for receiving the three-dimensional form data and the surface feature information output by the visual recognition module, executing point cloud structured conversion on the three-dimensional form data, extracting geometric features of an object through a neural network, and meanwhile, performing weight distribution on the surface feature information by adopting a feature attention mechanism to complete multi-feature fusion processing; according to the multi-axis cooperative manipulator provided with the end executor, the end executor integrates a touch sensing assembly used for touch sensing and an adsorption execution device used for assisting grabbing. By integrating the technologies of visual identification, multi-modal fusion, intelligent optimization, dynamic feedback and the like, the sensing precision, the environmental adaptability and the grabbing reliability of the system to object characteristics are improved.

The invention provides a dexterous hand multi-object stable grabbing method and system based on vision and touch perception. The dexterous hand multi-object stable grabbing method comprises the steps that RGB images and depth maps of target objects are collected through a monocular RGB-D camera, and dense point cloud data are generated; geometric features are extracted by using a three-dimensional point cloud neural network, and composite object distribution features are analyzed in combination with visual information; an initial grasping strategy is generated based on the features, actions are executed, and the joint state and contact force data are synchronously obtained in real time through body sensing and a fingertip force sensor; in the carrying process, multi-dimensional force perception and the joint state are fused to analyze object stress distribution and center-of-gravity shift; vision and force sensing data are used as input. Vision, body sensing and force sensing data are fused, the problems of three-dimensional structure recognition and dynamic stress regulation and control in multi-object composite grabbing are solved, compared with a single sensing scheme, the grabbing planning precision and the self-adaptive capacity in a complex scene are remarkably improved, and the method is particularly suitable for stable carrying of combinations of loose objects such as dinner plates carrying tableware.

The invention relates to a large model and small model collaborative robot operation action real-time control method and a large model and small model collaborative robot operation action real-time control system. The method comprises the following steps: firstly, collecting and preprocessing multi-modal data; carrying out data coding on the multi-modal data to obtain a feature vector; aligning the multi-modal data by using a cross-modal token alignment technology to obtain a feature representation; then training a neural network model by using the feature vector and the feature representation to obtain a trained large model; pruning, distilling and quantifying the trained large model to generate a small model; the small model is deployed to an edge computing device, the edge computing device obtains current instruction text data in real time and conducts reasoning on the current instruction text data, and an action plan of the robot is generated; and finally, the robot is controlled to operate and act in real time by means of action planning of the robot and feedback signals of the sensors. Compared with the prior art, the method has the advantages of low delay, high efficiency, capability of improving tactile perception, self-adaptive grabbing and real-time action planning and the like.

The invention discloses a large-deflection deformation flexible shaft hole assembly method and device based on tactile perception, storage equipment and a program product, and belongs to the technical field of robot assembly. The problem that an existing assembling method does not consider the influence of non-linear large-deflection deformation of the flexible shaft on the assembling precision of the shaft hole is solved. Based on pressure distribution data fed back by the tactile sensor, the deformation condition of the shaft can be estimated and adjusted, the flexible shaft workpiece makes effective contact with the rigid plane where the target hole is located, whether the shaft passes through the hole or not is monitored in real time in the blind hole searching process, and after the hole is searched, the mechanical arm is controlled to automatically align the shaft hole, so that the hole searching efficiency is improved. And the shaft insertion action is completed. The device is mainly used for shaft hole assembly of the large-deflection deformation flexible shaft workpiece.

The invention provides an interactive tactile glove system for astronaut training. The interactive tactile glove system comprises an upper computer virtual environment, a lower computer tactile perception glove and a tactile representation glove. The touch sensing glove is used for collecting temperature, humidity and pressure information of a hand and transmitting the information to the upper computer for processing through Bluetooth. The upper computer virtual environment is built based on a Unity 3D platform, various task scenes can be simulated, and corresponding tactile feedback signals are generated and transmitted. The tactile representation glove receives data transmitted by a virtual environment or the tactile perception glove, and real-time representation of temperature, force feedback and motion postures is achieved through an integrated semiconductor cooler, a vibration element, a bending sensor and other assemblies. According to the system, multi-modal tactile feedback can be provided in single astronaut fine operation training and cooperative operation of multiple astronauts, and the training effect and team adaptability are improved. The system not only has high integration level and stability, but also can provide multi-level and multi-mode tactile simulation according to task requirements, and is suitable for accurate training and remote operation in a complex task environment.

The invention relates to the technical field of robots. According to the touch sensing fingertip device, protection of a touch sensor in fine operation of a mechanical arm is achieved, and objects of sheet structures can be grabbed more accurately. Specifically, through the bionic fingernail part installed on the back side of the fingertip body, the protection part of the bionic fingernail part extends forwards and exceeds the highest point of the touch sensor, and a cantilever protection structure similar to a human fingernail is formed; the protection parts form a physical barrier (for example, the protection parts are preferentially contacted during grabbing) in a non-contact state by utilizing a reasonable coverage range of the bionic nail part, and meanwhile, when the protection parts are matched with fingers on the opposite side, the two corresponding protection parts can be matched to grab an object of a sheet-shaped structure; according to the design, the durability of the sensor in a complex environment is improved, and the accuracy of grabbing the sheet-shaped objects is improved.

The invention discloses a high-sensitivity tactile sensing system based on a magnetic cilia array, a sensor comprises the magnetic cilia array and a sensor array, and the magnetic cilia array is attached to the upper surface of the sensor array; the magnetic cilia array comprises a substrate and cilia structures which are orderly arranged and fixed on the substrate; the cilia structure is made of ecological silicone rubber mixed with magnetic powder, and a plurality of groups of sensors are adopted to form a sensor array to construct a sensing system. By optimizing the magnetization process, uniform distribution of the magnetic particles in each cilium is ensured, and the output stability and sensitivity of the sensor are improved; meanwhile, the multi-sensor array layout is adopted, and high-precision sensing of multi-dimensional tactile information such as pressure, direction and vibration is achieved.

The invention discloses a self-adaptive tactile feedback robot force-position hybrid control system and method, and relates to the technical field of industrial robot precision control. Comprising a bionic tactile sensing module, the output end of the bionic tactile sensing module is connected with a pulse coding module, the output end of the pulse coding module is connected with a force-position cooperative controller, and the output end of the force-position cooperative controller is connected with a dynamic impedance regulator. Dynamic decoupling control over the contact force and the position error is achieved through a double-closed-loop framework, accurate control over the force and the position is taken into consideration for the robot in the complex and changeable assembling environment, and the problem that force control and position control interfere with each other in a traditional control method is solved.

The utility model discloses a multi-mode fusion touch fingertip module which comprises a supporting layer (107). The outer surface of the supporting layer (107) is provided with a proximity sense sensing layer (101) used for sensing the distance, a temperature site (102) used for sensing the temperature, a touch sense / slip sense sensing layer (103) used for sensing the touch sense, a control element (104), an electrode layer (105) used for transmitting signals and a force sensing layer (106) used for sensing the force. According to a three-dimensional force three-dimensional tactile sensing network, multi-mode sensor signals can be obtained, a multi-branch tactile neural network is constructed by using the signals, and a tactile fingertip module is formed, so that the shortages of two-dimensional tactile sensing can be made up, and three-dimensional characteristics of tactile sensing can be obtained; that is to say, richer haptic information such as output magnitude, direction, acting position, spatial distribution of force, dynamic force time sequence characteristics, spatial distribution of temperature and the like can be decoupled, various characteristics of the object are extracted, and the accuracy of object haptic recognition is improved.

The invention relates to the technical field of robot tactile perception, in particular to a laparoscopic surgery robot tactile interaction system and method, and the system comprises an F / T sensor which is used for obtaining and detecting sensor information of contact force between a tail end surgical instrument and patient tissue; the data processor is used for detecting the contact force between the tail end surgical instrument and the tissue of the patient according to the information of the sensor, converting the contact force into feedback force which can be sensed by an operation object, converting the feedback force into control parameters of the force feedback device, and smoothly optimizing the control parameters; and the force feedback device is used for controlling and driving a force feedback type main manipulator of the laparoscopic surgery robot according to the control parameters after smooth optimization so as to transmit feedback force to an operation object for sensing. According to the invention, an operator can sense the contact force between the end surgical instrument and the tissue of a patient, the operator can be prevented from sensing abrupt change, the smoothness of tactile sensing is ensured, and a basic guarantee is provided for accurate tactile judgment of the operator.

The invention provides an underwater static pressure self-balancing visual touch perception device and method. The device comprises an elastic body, a hexagonal tray, a light source, a camera, a protective cover, a base, a water inlet pipe, a water outlet pipe and a computer. The elastomer is used for contacting an object, and a plurality of micron-sized through holes for balancing internal and external water pressure are formed in the surface; the elastomer is arranged on the inner side of the hexagonal tray, and the RGB three-color light source is arranged on the outer side to realize uniform distribution of light; the camera collects a light intensity image reflected by the elastomer; the protective cover is fixedly connected to the base and used for isolating external light and fixing the hexagonal tray. A camera is mounted on the base; the computer is used to model the acquired images or videos as different haptic features.

The invention discloses a robot system with tactile perception, and belongs to the technical field of tactile robots. The problem that an existing robot is poor in environment pressure sensing capacity is solved. Comprising a head module, an integrated vision-inertial navigation sensing module and a head controller, two side surfaces are provided with a pair of rotatable connecting ends, and the outer surface is provided with a tactile sensor; the head controller transmits data to the upper computer through the communication module; the driving body module comprises a plurality of modularized joints which are connected end to end, touch sensors are arranged on the two side faces of each modularized joint, and the adjacent modularized joints are orthogonally connected; the modularized joint is integrated with a joint controller and a joint steering engine; the tail module integrates a tail controller and a tail steering engine, and tactile sensors are arranged on the two side faces of the tail module. The tail controller carries out data transmission with the head controller through the adjacent previous joint controller in sequence, and the head controller receives a control instruction of the upper computer and carries out data transmission with all other controllers. According to the invention, the environmental pressure can be sensed in all directions.

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 relates to the technical field of tactile sensing, in particular to a three-dimensional array type magnetic tactile sensor and a manufacturing method thereof. The three-dimensional array type magnetic tactile sensor comprises a flexible circuit board layer, an elastic layer and a flexible magnet layer which are sequentially stacked and bonded from bottom to top, when the flexible magnet layer deforms due to external pressure, the surrounding magnetic field intensity is changed, and the flexible circuit board layer measures external force by sensing the magnetic field change of the flexible magnet layer. The elastic layer is used for expanding the external force measurement range of the flexible circuit board layer. The flexible magnet layer comprises a top-layer flexible body and a plurality of flexible magnets embedded in the top-layer flexible body, and the flexible magnets are used as contacts. The device simulates human hand touch perception, has a wide force measurement range, can accurately detect tiny force change, and improves sensitivity.

The embodiment of the invention provides a touch sensing system and method, electronic equipment, a storage medium and a program product. The touch sensing system comprises a contact assembly, a projection assembly, a collection assembly and a processing assembly, and is configured to be capable of being in contact with an external object and generating deformation; the projection assembly is configured to project an active light field with a time modulation characteristic to a first surface of the contact assembly, the active light field is projected on the first surface to form a plurality of pattern areas, the light intensity of adjacent pattern areas changes based on different time sequence codes, and the first surface is opposite to a second surface, making contact with an external object, of the contact assembly; the acquisition assembly comprises a plurality of acquisition units arranged in an array, and is configured to acquire a plurality of pattern areas and output a time stamp acquisition data sequence.

The invention provides a multi-modal intelligent interaction optimization method and system, and the method comprises the steps: obtaining text instruction data according to a voice instruction of a user, and calculating the voice confidence; identifying and positioning an object in an image shot by the camera to obtain visual data, and calculating visual confidence; tactile data of the intelligent device and the contacted object are obtained according to the tactile sensor, and the tactile confidence coefficient is calculated; and then, adjusting the weight of each perception in a preset decision model according to the confidence of the three perceptions. And finally, inputting the text instruction data, the visual data and the tactile data into the decision model after weight adjustment to obtain a task execution strategy. According to the method and the system disclosed by the invention, voice, vision and touch perception can be combined, meanwhile, a confidence evaluation mechanism is introduced, multiple verification is performed on task execution, and dynamic adjustment is ensured to be made according to accuracy and reliability of different perception data.

The invention discloses a multi-mode visual tactile sensor and a sensing method thereof. The sensor is composed of a sensing cover and an imaging box body, the sensing cover is fixed on the imaging box body, the sensing cover is provided with a flexible sensing layer, an embedded mark point array combining inert ink and thermochromic ink is arranged in the sensing layer, during tactile sensing, a light source is provided through the imaging box body, and multi-mode sensing data is obtained. Therefore, displacement tracking and temperature sensing are realized at the same time. According to the invention, multi-mode sensing of five modes of a two-dimensional texture pattern, a three-dimensional texture image, a three-dimensional displacement field, a three-dimensional force field and a two-dimensional temperature field can be realized under a single optical frame, real-time co-registration measurement can be realized, and a high-integration-level solution is provided for a robot touch system. The problems that an existing visual tactile sensor cannot sense multi-mode information synchronously, force field reconstruction calculation is complex, and temperature sensing capacity is lacked are solved, and the visual tactile sensor is suitable for application scenes such as robot tactile sensing, man-machine interaction, intelligent artificial limbs and industrial detection.

The invention belongs to the field of tactile perception, and relates to a tactile spatial position recognition system and method based on extraterritorial stimulation. The system comprises tactile feedback electrodes at finger pulps, extraterritorial stimulation electrodes on the outer sides of the finger pulps and a control module. The extraterritorial stimulation electrodes are at least associated with the tactile feedback electrodes adjacent to the extraterritorial stimulation electrodes; the control module controls whether the associated extraterritorial stimulation electrode works or not according to the working state of the tactile feedback electrode and the incidence relation between the electrode stimulation site and the virtual tactile sense; when the tactile feedback electrode works, the control module applies micro-current to the associated extraterritorial stimulation electrode so as to generate tactile stimulation to the skin outside the finger pulp and send out a space guide positioning signal. The extraterritorial stimulation electrodes are arranged on the outer sides of the finger pulps, and when the associated tactile feedback electrodes work, the corresponding extraterritorial stimulation electrodes work, so that a receptor can more accurately judge the positions of the tactile feedback electrodes for applying micro-current to the finger pulps, and the tactile spatial position recognition capability of the receptor is improved.

The invention discloses a facial robot expression and action precise control system based on multi-mode perception, and the system comprises a multi-mode perception module which is used for integrating the information of various perception modes, such as vision, sound, touch and bio-electricity signals at the same time; the multi-mode sensing module comprises a visual sensing module, a sound sensing module, a touch sensing module and a bio-electricity signal sensing module. According to the method, information of various sensing modes such as vision, sound, touch and bio-electricity signals can be integrated at the same time, comprehensive analysis is carried out through an advanced artificial intelligence algorithm, and therefore accurate and natural control over facial expressions and actions of the facial robot is achieved. The intelligent level and interaction experience of the robot can be greatly improved, and the robot can better adapt to complex and changeable environments and user requirements.

The utility model relates to the technical field of sensors, in particular to a visual touch sensor. According to the utility model, the colloid on the transparent plate is in contact with an object, the single-sided mirror is arranged opposite to the colloid on the opening, the camera component performs visual detection on the deformation condition of the colloid reflected by the single-sided mirror, and the effect of clamping different objects is achieved through the deformation of the colloid, so that the tactile perception capability of the visual tactile sensor is realized; the robot is simple in structure, low in cost and high in adaptability, and can be widely applied to the fields of object grabbing, flexible operation, touch perception in rehabilitation prostheses and the like; and meanwhile, the number of parts required by the visual tactile sensor is reduced, the working stability of the visual tactile sensor can be effectively improved, the failure rate is low, and the reliability is relatively high.

The invention relates to the technical field of sensors, in particular to a flexible multifunctional touch sensing electronic skin and application, and the flexible multifunctional touch sensing electronic skin comprises a deformation module, an imaging module and a deep learning algorithm processing module; the deformation module comprises a mark layer provided with a mark pattern; the deformation module is used for capturing deformation information of the marking layer caused by external stimulation in real time; the imaging module comprises an embedded camera; the imaging module is used for acquiring a real-time image of the marking layer of the deformation module and reflecting the characteristics of tactile stimulation through image data; and the deep learning algorithm processing module is used for processing the image data captured by the imaging module in real time through a deep learning algorithm, extracting feature information in the tactile signal and further analyzing the property and the distribution of the external stimulation. According to the method, the deep learning algorithm and the visual tactile perception are combined, so that the tactile perception precision is improved, breakthrough is realized in the aspects of three-dimensional force decoupling and real-time recognition of complex actions, and the method has higher application potential and wide prospects.

The invention relates to an event-driven tactile sensing method and system based on a pulse graph neural network, and belongs to the technical field of tactile sensing and robot control. The method comprises the following steps: S1, extracting main features from data collected by an event-driven touch sensor; s2, encoding the main features extracted from the tactile sensor data; s3, using a spiking neural network to further learn feature embedding; s4, the encoded features are processed through a graph neural network; and S5, identifying the category or state of the target object by adopting a voting mechanism. According to the scheme, through the graph neural network, the graph based on the space structure of the tactile sensing unit can be automatically constructed, and local and global features are efficiently extracted; the pulse neural network is used for processing event-driven data, so that the energy consumption is remarkably reduced and the calculation efficiency is improved; the method has strong generalization ability, can adapt to different tactile sensor configurations and application scenes, and has excellent performance when processing real-time tactile perception tasks.

The invention discloses a multi-parameter dynamic coding method for tactile feedback. The method comprises the following steps: arranging a multi-channel electrode array in a tactile sensing area, and establishing a corresponding relation between each channel of a multi-channel array electrode and a spatial position in the tactile sensing area through spatial coding; calibrating the minimum value and the maximum value of various types of electrode stimulation parameters reflecting the touch perception degree to obtain a dual-threshold calibration result; performing intensity coding according to the double-threshold calibration result; constructing a type code, wherein the type code reflects a corresponding relation between the frequency interval and the touch induction type; and generating a parameter dynamic mapping model based on the intensity code and the type code, wherein the parameter dynamic mapping model reflects a corresponding relation between an interaction characteristic between the touch sensing area and a target and an electrode stimulation parameter combination sensed by the touch sensing area. The method can be widely applied to man-machine interaction scenes needing tactile feedback.

The invention discloses a six-axis distributed force tactile sensing method, system and terminal based on binocular tactile sense, and the method comprises the steps: obtaining virtual binocular tactile sense, collecting a curved surface result of a target object, and calculating a rotation axis and six-axis distributed force of a contact area after the target object is contacted, and iteratively updating a plurality of parameters of the spring-damping network model so as to further collect geometric space characteristics of the target object when the target object is touched. According to the method, on the basis of a double-mirror reflection double-vision tactile platform, virtual double-vision tactile sense is constructed, three-dimensional geometric deformation of a contact surface is reconstructed, a spring-damping network model is adopted, and the six-axis force of the fingertip is estimated, so that the range, precision and calculation efficiency of the model method in force distribution reconstruction are improved.

The invention provides an industrial robot self-adaptive grabbing method based on multi-modal sensing, which comprises the following steps of: 1, acquiring multi-modal data of an object and an environment through a multi-modal sensing module; the multi-mode sensing module comprises at least two sensing modules of a visual sensing unit, a touch sensing unit, a force sensing unit and an auditory sensing unit; 2, preprocessing and feature extraction are carried out on the multi-modal data, feature information of different modals is fused through a multi-modal fusion algorithm, and comprehensive object description information is generated; 3, generating an optimal grabbing strategy based on the comprehensive object description information; wherein the grabbing strategy comprises the position and posture of a grabbing point, a grabbing path and grabbing force; and fourthly, the industrial robot executes the optimal grabbing strategy, the first step to the third step are repeated, and the grabbing strategy is adjusted in a self-adaptive mode till grabbing is completed. Stable and efficient grabbing can be achieved.

The invention discloses a paper folding structure inductance type self-decoupling miniature six-dimensional force sensor, which belongs to the technical field of force sensors and comprises a base, a folding flexible circuit board, a metal shell, a communication cable, a coil inductance measuring circuit and an elastic body. The folding flexible circuit board comprises a coil array and an inductance measuring circuit, the coil array is folded on the upper surface and the four side faces of the base, the inductance measuring circuit is folded at the bottom of the base, and a communication cable is led out of the inductance measuring circuit. The metal shell is arranged above the base and surrounds the surface, except the bottom surface, of the folding flexible circuit board; an elastic body is arranged between the metal shell and the base. The elastomer converts six-dimensional force borne by the metal shell into six-dimensional displacement. According to the sensor, the characteristic that the eddy current effect is sensitive to normal displacement and insensitive to tangential displacement and rotation is utilized, self-decoupling measurement of six-dimensional displacement of the metal shell is achieved in combination with three-dimensional coil layout, and therefore self-decoupling six-dimensional force measurement is achieved, and the sensor can be integrated to the fingertip of the dexterous hand to provide endogenous tactile perception.

An embodiment of the utility model discloses a visual tactile sensor, which relates to the technical field of sensors and comprises a base, a flexible plate, an image acquisition device and a plane mirror. The flexible plate is arranged on the base, the image acquisition device is arranged on the base, the image acquisition device is located on one side of the flexible plate, and the plane mirror is obliquely arranged on the upper side of the flexible plate. The layout between the flexible plate and the image acquisition device can be changed through the plane mirror, the size of the visual tactile sensor in the height direction is greatly reduced, and the size of the visual tactile sensor is reduced. According to the scheme, through the innovative structural design of reflection imaging of the plane mirror, on the premise that the tactile perception precision is ensured, the problem that the size of a traditional visual tactile sensor is too large due to vertical imaging layout is solved, meanwhile, multiple technical requirements of environmental adaptability, cost controllability and the like are taken into consideration, and the visual tactile sensor is suitable for popularization and application. And better hardware support is provided for scenes such as refined operation and man-machine interaction of the robot.

The invention discloses a wearable device tactile perception method and system based on an improved graph convolutional neural network, and the method comprises the steps: obtaining tactile data according to a pre-constructed contact simulation platform, and carrying out the processing of the tactile data through employing a noise region-based image enhancement algorithm, and obtaining target tactile data; optimizing the convolutional neural network according to a preset probability random switching activation function to obtain a target convolutional neural network; inputting the target tactile data and annotation data corresponding to the target tactile data into the target convolutional neural network by adopting a convolutional layer filter difference regularization algorithm, and performing iterative training on the target convolutional neural network to obtain a tactile perception model; and inputting the obtained real-time tactile perception data into the tactile perception model, and outputting a tactile perception result by the tactile perception model. The accuracy and stability of the tactile sensing system can be improved, and tactile sensing with high resolution and wide dynamic range is realized.

The invention discloses a vision-based high-density three-dimensional force sensing array system and a three-dimensional force distribution identification method thereof. The system comprises a first force sensing layer, a second force sensing layer, a support force bearing layer, an LED lighting unit, a light-transmitting reference plate, a camera and a supporting shell box body. The second force sensing layer is a high-density array formed by independently distributed cylinder and hemisphere elastic structure units; and the light-transmitting reference plate, the LED lighting unit and the camera form an optical imaging assembly. When an external object is in contact with the surface of the array, each structural unit deforms independently, a camera captures a deformation image, features are extracted through an image processing algorithm, and three-dimensional force distribution of a contact area is solved according to a pre-calibrated image-mechanics mapping model. The system can reconstruct the three-dimensional contour form of a contact object in real time and perceive the force distribution characteristics of the contact object, and a high-precision and low-cost force touch perception solution is provided for the fields of robot touch recognition, human-computer interaction, safety monitoring and the like.