WO2023277794A2 - Force sensors and devices incorporating force sensors - Google Patents

Force sensors and devices incorporating force sensors Download PDF

Info

Publication number
WO2023277794A2
WO2023277794A2 PCT/SG2022/050387 SG2022050387W WO2023277794A2 WO 2023277794 A2 WO2023277794 A2 WO 2023277794A2 SG 2022050387 W SG2022050387 W SG 2022050387W WO 2023277794 A2 WO2023277794 A2 WO 2023277794A2
Authority
WO
WIPO (PCT)
Prior art keywords
sensor
force
layer
contact
force sensor
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/SG2022/050387
Other languages
English (en)
French (fr)
Other versions
WO2023277794A3 (en
Inventor
Zeyu LU
Haoyong Yu
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National University of Singapore
Original Assignee
National University of Singapore
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by National University of Singapore filed Critical National University of Singapore
Priority to CN202280040659.2A priority Critical patent/CN117501082A/zh
Priority to EP22833769.7A priority patent/EP4363819A4/en
Priority to JP2023580792A priority patent/JP2024528541A/ja
Priority to US18/286,940 priority patent/US12510426B2/en
Publication of WO2023277794A2 publication Critical patent/WO2023277794A2/en
Publication of WO2023277794A3 publication Critical patent/WO2023277794A3/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00—Controls for manipulators
    • B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
    • B25J13/085—Force or torque sensors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/0061—Force sensors associated with industrial machines or actuators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00—Controls for manipulators
    • B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
    • B25J13/081—Touching devices, e.g. pressure-sensitive
    • B25J13/082—Grasping-force detectors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00—Controls for manipulators
    • B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
    • B25J13/081—Touching devices, e.g. pressure-sensitive
    • B25J13/084—Tactile sensors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J15/00—Gripping heads and other end effectors
    • B25J15/08—Gripping heads and other end effectors having finger members
    • B25J15/10—Gripping heads and other end effectors having finger members with three or more finger members
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Program-controlled manipulators
    • B25J9/16—Program controls
    • B25J9/1628—Program controls characterised by the control loop
    • B25J9/1633—Program controls characterised by the control loop compliant, force, torque control, e.g. combined with position control
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/12—Measuring force or stress, in general by measuring variations in the magnetic properties of materials resulting from the application of stress
    • G01L1/122—Measuring force or stress, in general by measuring variations in the magnetic properties of materials resulting from the application of stress by using permanent magnets
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/14—Measuring force or stress, in general by measuring variations in capacitance or inductance of electrical elements, e.g. by measuring variations of frequency of electrical oscillators
    • G01L1/142—Measuring force or stress, in general by measuring variations in capacitance or inductance of electrical elements, e.g. by measuring variations of frequency of electrical oscillators using capacitors
    • G01L1/146—Measuring force or stress, in general by measuring variations in capacitance or inductance of electrical elements, e.g. by measuring variations of frequency of electrical oscillators using capacitors for measuring force distributions, e.g. using force arrays
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/16—Measuring force or stress, in general using properties of piezoelectric devices
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/18—Measuring force or stress, in general using properties of piezo-resistive materials, i.e. materials of which the ohmic resistance varies according to changes in magnitude or direction of force applied to the material
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/20—Measuring force or stress, in general by measuring variations in ohmic resistance of solid materials or of electrically-conductive fluids; by making use of electrokinetic cells, i.e. liquid-containing cells wherein an electrical potential is produced or varied upon the application of stress
    • G01L1/205—Measuring force or stress, in general by measuring variations in ohmic resistance of solid materials or of electrically-conductive fluids; by making use of electrokinetic cells, i.e. liquid-containing cells wherein an electrical potential is produced or varied upon the application of stress using distributed sensing elements
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/0061—Force sensors associated with industrial machines or actuators
    • G01L5/0076—Force sensors associated with manufacturing machines
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/16—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force
    • G01L5/161—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force using variations in ohmic resistance
    • G01L5/162—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force using variations in ohmic resistance of piezoresistors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/16—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force
    • G01L5/165—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force using variations in capacitance
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/16—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force
    • G01L5/169—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring several components of force using magnetic means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/22—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring the force applied to control members, e.g. control members of vehicles, triggers
    • G01L5/226—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes for measuring the force applied to control members, e.g. control members of vehicles, triggers to manipulators, e.g. the force due to gripping

Definitions

  • This disclosure generally relates to force sensors, robotic devices incorporating a force sensor and methods of tactile force sensing.
  • Tactile sensing technologies enable robotic operations to perform complex tasks and gather information in complex environments.
  • tactile sensing technologies based on piezoresistive, optical, capacitive, barometric, or magnetic principles are known.
  • Tactile sensing may involve several kinds of force sensing including: normal forces and shear forces. The forces may be applied at one point or may be distributed over a larger area. Different operations or environments may require measurement of forces at different resolutions. In some robotic operations, it may be beneficial to obtain the location of a contact force.
  • a force sensor comprising: a contact arrangement for transmitting a contact force to a force sensor assembly, the force sensor assembly comprising: a first sensor sensing, and producing an output from, a normal contact force component of the contact force; and a body moveable on transmission of the contact force to the force sensor assembly; and a second sensor for sensing, and producing an output from, a relative displacement of the body relative to the second sensor, a tri-axis contact force being determined from the relative displacement.
  • the contact arrangement may comprise a deformable substrate that deforms under the contact force.
  • the deformable substrate may be an elastomeric substrate.
  • the body may comprise a magnet and the second sensor is one or more Hall effect sensors.
  • the body may comprise a plurality of magnets.
  • the body may comprise a rigid layer comprising the magnet or magnets, and a deformable layer one side of which is fixed to the rigid layer and an opposing side of which is fixed relative to the Hall effect sensor, the deformable layer permitting displacement, under the contact force, of the rigid layer relative to the Hall effect sensor.
  • the second sensor may be housed in a chamber.
  • the force sensor may further comprise a base structure for incorporating the force sensor into a device, wherein the base chamber is incorporated into, or abuts, the base structure.
  • the body may be embedded in a substrate between the first sensor from the second sensor.
  • the first sensor may comprise one or more sensors each being one of a matrix piezoresistive sensor, a piezoelectric sensor, a capacitive sensor, a triboelectric sensor, and an optical sensor.
  • the force sensor may form a multi-layer structure with a top layer comprising the contact arrangement, second layer and a first layer between the top layer and second layer, the first layer and second layer comprising respectively different ones of the first sensor and second sensor.
  • the body may be disposed between the first layer and second layer.
  • the second sensor may be in the second layer.
  • a force sensor device comprising an array of force sensors as described above.
  • a robotic device comprising the force sensor as described above, or the force sensor device as described above.
  • the robotic device may be a gripper.
  • a prosthesis comprising the force sensor described above, or the force sensor device described above.
  • the prosthesis may be one of a prosthetic arm, prosthetic upper limb or prosthetic lower limb.
  • a robotic hand comprising: a palm portion; a plurality of finger portions; a write portion; a plurality of force sensors as described above, located at contact points for contacting an object during use; and a processor for: receiving an output from each of the first sensor and second sensor; determining from the output, one or more fast-adapting (FA) responses and one or more slow-adapting (SA) responses; and identifying an extrinsic contact state (ECS) of the object based on the one or more FA responses and one or more SA responses.
  • FA fast-adapting
  • SA slow-adapting
  • Identifying the ECS may comprise determining a first order response and a second order response from the one or more FA responses and one or more SA responses.
  • the first order response may comprise one or both of a normal force and a shear force
  • the second order response may comprise a time-varying pattern.
  • Also disclosed herein is a computer implemented method for identification of extrinsic contact states (ECSs) of a robotic hand with respect to an object, the method comprising: receiving tactile sensing signals from each finger section of the robotic hand, the tactile sensing signals comprising fast-adapting (FA) response signals and slow- adapting (SA) response signals; processing the tactile sensing signals by a decoder model to determine tactile event data associated with each finger section of the robotic hand; processing the determined tactile event data by a machine leaning model to determine an ECS of the robotic hand with respect to the object.
  • FA fast-adapting
  • SA slow- adapting
  • Figure 1 (a) illustrates a side view of a force sensor, which illustrates the multilayer structure and its components; (b) illustrates a schematic diagram of the force sensor;
  • Figure 2 illustrates a side view illustrating the anticipated deformation of elastomer substrates when the tactile sensor is in external contact force that consists of a normal force vector and a tangential force vector;
  • Figure 3 illustrates a layer of matrix piezoresistive sensors that are made up of multiple cross conductive wires and flexible conductive materials whose electrical resistance changes due to applied mechanical load;
  • Figure 4 illustrates a representative magnetic field vector from a cylinder magnet in which field lines point from north pole (N) to south pole (S) and the strength of magnetic field is inversely proportional to the distance from magnet;
  • Figure 5 illustrates a rigid bone structure that is magnetized by mounting a magnet inside, which functions as a carrier to move the magnets corresponding to the contact force;
  • Figure 6 illustrates the anticipated change of elastomer shape and local magnetic field while the layer of bone structure being applied by a tangential contact force (F) to the left;
  • Figure 7 illustrates the anticipated change of elastomer shape and local magnetic field while the layer of bone structure being applied by a tangential contact force (F) to the right;
  • Figure 8 illustrates the anticipated change of elastomer shape and local magnetic field while the layer of bone structure being applied by a normal contact force (F) from the top;
  • Figure 9 illustrates an example application of the force sensor in which a robotic gripper is integrated with the force sensor
  • Figure 10 illustrates another example application of the force sensor in which a robotic hand/prosthetic hand is integrated with the force sensor as a tactile sensorized fingertip;
  • Figure 11 illustrates another example application of the force sensor in which a robotic leg/prosthetic leg is integrated with the force sensor as a tactile sensorized fingertip;
  • Figure 12 illustrates a 4 by 4 matrix piezoresistive sensors as the FA-I layer in a force sensor and an associated circuit schematic;
  • Figure 13 illustrates a multilayered structure and characterization performance of a force sensor
  • Figure 14 illustrates a finger mechanism structure of a gripper incorporating a force sensor
  • Figure 15 illustrates an overview of tactile sensing solution and signal transmission for a gripper incorporating a force sensor
  • Figure 16 illustrates various grasping configurations of a gripper incorporating a force sensor
  • Figure 17 illustrates a robotic hand incorporating force sensors and analogizes the robotic hand with a human hand
  • Figure 18 illustrates a force sensors integration and data transmission for a robotic hand
  • Figure 19 illustrates a data flow graph at the index distal finger section when the robotic hand grasping a cylinder-shaped object in a force-closed manner
  • Figure 20 illustrates tactile sensing signals and a CNN architecture used to identify the 9 dominant ECSs
  • Figure 21 illustrates experiments performed using a robotic hand incorporating the force sensor
  • Figure 22 illustrates an experimental setup of applying ECS identification capabilities to perform ball-hit recognition.
  • This disclosure relates to force sensors (also referred to as GTac or GTac sensor or a tactile sensor or a tactile force sensor) for tactile force sensing.
  • the disclosure also relates to methods of measuring matrix normal contact force and internal tri-axis forces using the GTac sensor.
  • the GTac sensors may serve as low-cost biomimetic tactile sensor for domestic robots, where the solution can be customized depending on the needs of the robotic operation. For example, a large sensing area may be provided for robot arms and a small sensing area for robot fingertips.
  • the GTac sensors may also be incorporated in robotic prostheses to be safely controlled on amputees.
  • the GTac sensors can be used to provide a large-area biomimetic tactile sensing capability for lower-limb prostheses and upper-limb prostheses due to high sensing capabilities, high extensibility, and low cost of its design.
  • GTac in some exemplary embodiments decouples dense extrinsic normal force sensing and intrinsic tri-axis force sensing capabilities mimicking the tactile sensing functions of human fingertip.
  • GTac of some exemplary embodiments adopts a human- skin-inspired multilayer structure that consists of a matrix piezoresistive sensors, a magnetic bone structure, silicone elastomer substrates and a Flail effect sensor.
  • Exemplary GTacs sensors can estimate dense normal contact force and contact shear force.
  • GTacs advantageously provide improved tactile sensing in terms of sensing abilities, simplicity, sensitivity, robustness, and form factor.
  • GTacs of some embodiments perceive rich contact information, namely contact force magnitude, contact force location, and contact force direction.
  • the contact information advantageously contributes to improved safety and stability in controlling robots/human-robot interactions. While interacting with objects or human, robots are required to actively perceive the situation of interaction and make decision according to the situation. For example, contacts happen when robots touch objects. Measuring the contact force magnitude allows estimation an object's kinesthetic properties, allows adjustments for stability of grasping objects, safety of interacting with human, and effectiveness of manipulating objects. Measuring contact locations can be used to estimate the joint level torque exerted by objects. Measuring contact force direction is useful for perception in manipulating objects and for estimating stability of objects during manipulation.
  • the force sensors may incorporate two sensing principles: piezoresistive sensing principle and Hall effect based sensing.
  • the force sensor may include piezoresistive sensors, Hall effect sensors, magnets, 3D printed structures, and elastomer substrates.
  • There may be provided a multilayer structure that makes the external contact force transmit from the contact surface to the sensing components of the force sensor. Signals from the sensing components can be processed to determine forces applied to the force sensor.
  • Some force sensors may include elastomer substrates that are used to build soft contact surface and/or serve as a force transmission medium.
  • the piezoresistive sensors respond to normal contact force by decreasing the electrical resistance at positions corresponding to the contact force.
  • the Hall effect sensor can measure the change of local magnetic field caused by the external contact force changing position of a magnetized bone structure. The above signals all can be collected and processed by a processor or a microcontroller provided in the force sensor.
  • Figure 1 (a) shows side a view of a tactile force sensor 100. From the side view, the sensor 100 adopts a multilayer structure. From the top, the contact surface is on an flexible - e.g. elastomer or elastomeric - substrate 2a (also referred to as tap elastomer).
  • the substrate 2a can deform corresponding to the contact force and transmit contact force to the next layer, i.e., matrix piezoresistive sensors 3 (also referred to as a normal force sensing laminate matrix).
  • matrix piezoresistive sensors 3 also referred to as a normal force sensing laminate matrix.
  • the pressure/mechanical strain is transmitted to a region of piezoresistive sensors 3 so that the electrical resistance is reduced at the region with pressure.
  • the electrical resistance of 3 may be linearized with the applied pressure.
  • Another flexible - e.g. elastomer or elastomeric - substrate 2b (also referred to as a flat elastomer) is attached on a structure - referred to as bone structure 4a - and the base chamber 4b, the rigid body comprising piezoresistive sensor 3, bone structure 4a, and magnet 5.
  • the rigid body may therefore experience displacement in tri-axis (i.e. in three dimensions) with respect to the base chamber 4b under an applied contact force. This can change the local magnetic field 5a.
  • the local magnetic field from magnet 5 should be able to penetrate the base chamber 4b and should be detected by the Hall effect sensor 6.
  • the Hall effect sensor 6 used could be provided using the MLX90393 integrated circuit chip (Melexis Co.
  • the signals generated by the Hall effect sensor 6 can be read through an I2C bus or other communication bus.
  • the output data generated by the Hall effect sensor 6 includes the magnetic strength value in x-y-z axis and temperature.
  • the digital output of the Hall effect sensor 6 is read by I2C pins on Engineering Mega2560 or other processor, for determining one or both of normal and shear contact forces.
  • an object 1 applies external force F on the contact surface of 2a.
  • the elastomer substrate 2a is anticipated to be deformed, to transmit the contact force to a mechanical strain on 3, to transmit the contact force to a deformation of elastomer substrate 2b.
  • the direction of the displacement vector of 4a is aligned with the direction of the tangential contact force vector. Therefore, the local magnetic field is being changed accordingly.
  • GTac sensor 100 can estimate the extrinsic arrayed (4 x 4 matrix) normal contact force in its elastomer substrate 2a (designed based on the Meissner's corpuscles of the human skin and also referred to as the fast-adaptive (FA)-I layer).
  • the elastomer substrate 2a may be 0.5 mm thick.
  • the sensor 100 may measure a tri-axis gross contact force in the bone structure layer 4a (designed based on Ruffini cylinders of the human skin and also referred to as the slow-adaptive (SA)-II layer). In this function, the bone structure layer 4a operates in concert with layers 2b and 4b.
  • the SA-II layer may be 3 mm thick or any other appropriate thickness.
  • the joint-level torque in both the FA-1 and SA-II layers may be estimated based on known geometrical dimensions when an external contact force is applied on the top layer 2a. More specifically, GTac transforms the normal extrinsic contact force into the reduction of the resistance and transforms the gross triaxis force into a local magnetic flux density change. The resistance and local magnetic flux density are measured using piezoresistive sensors and Hall sensors independently and simultaneously. Each GTac sensor 100 can obtain 19 tactile signals consisting of 16 (4 x 4 matrix) from the FA-I layer and 3 from the SA-II layer.
  • the contact location estimation of GTac may be obtained by a weighted average of the detected pressure at each sensing point as follows.
  • R r c is the signal reading from the FA-I layer in row r and column c
  • e is the spatial resolution of the FA-I layer
  • e 2.5mm, for example.
  • the external contact force can deform the elastomer substrate on the contact surface. This elastomer mechanically buffers the pressure in the case of sharp contact and thereafter delivers the pressure from the contact surface to the FA-I layer whose electrical resistance is reduced because of the mechanical strain.
  • the contact force is transmitted to the bone structure, deforming the flat elastomer relative to the base chamber.
  • the bone structure can move along the tri-axis relative to the Hall effect sensor, changing the local magnetic flux density.
  • This change in the local magnetic flux density can be measured by the Hall sensor and used to estimate the shear contact force.
  • the representation of the composition of force sensing on a GTac is the hybrid result of the FA-I and SA-II signals.
  • the linear relationship between the tri-axis contact force and GTac sensing signals can be expressed as of arrayed FA I signals in the 4 x 4 matrix.
  • FIG. 13 illustrates a biomimetic tactile sensor GTac 1300.
  • GTac 1300 unit consists of a flexible substrate - e.g. tap elastomer 1310 - a flat elastomer 1350, a piezoresistive sensor laminate (4 x 4) 1320, a polylactide bone structure 1330, a cylinder neodymium (NdFeB) magnet or other magnet 1340, a base chamber 1380, and a PCB with an integrated Flail sensor 1370.
  • a flexible substrate e.g. tap elastomer 1310 - a flat elastomer 1350
  • a piezoresistive sensor laminate (4 x 4) 1320 a polylactide bone structure 1330
  • a cylinder neodymium (NdFeB) magnet or other magnet 1340 a base chamber 1380
  • PCB with an integrated Flail sensor 1370.
  • the arrayed normal force sensing laminate i.e., piezoresistive sensors 1320
  • an elastomer substrate 1310 is placed on one side of it as the soft contact surface.
  • the other side of the laminate is attached to the next layer, a rigid bone structure 1330 magnetized by mounting the cylindrical NdFeB magnet 1340.
  • a flat elastomer substrate 1350 that is attached to the base chamber 1380 that integrates the Flail effect sensor 1370. All the elastomer substrates 1310, 1350 were made by casting and drying (12 hours) liquid silicone rubber (Ecoflex 00-50, Smooth-On Inc.) in customized molds, with an elastic modulus of 83 kPa.
  • Both layers of GTac could be customized to various shapes for different purposes.
  • the customizable variables in GTac included the piezoresistors in FA-I layer, the bone structure, the ferromagnetic marker, the elastomers in SA-II layer as well as the PCB. All the layers could be stuck together using an adhesive, such as Cyanolube Cyanoacrylate (Electrolube Co. Ltd).
  • the polylactide bone structures and customized molds could be printed by the Ultimaker S5 using PLA White (Ultimaker Co. Ltd.). Other materials for each component can be used as desired and the proposed materials are for illustration purposes only.
  • the Flail sensor was an MLX90393 integrated circuit chip (Melexis Co. Ltd.).
  • the MLX90393 Qwiic Magnetometer (SparkFun Co. Ltd.) was used in the characterization experiments.
  • the matrix piezoresistive sensor 3 consist of a piezoresistive material 3a and conductive wires 3b.
  • the piezoresistive materials 3a may comprise Velostat/Linqstat whose electrical resistance would be changed by applied mechanical strain.
  • the conductive wires 3b may be made flexible so that the piezoresistive sensors 3 can be deformed into different shapes, which may help build a well compatible contact surface.
  • the conductive wires 3b may be routed cross over rows and columns to form grid. However, none of the wires are directly in contact since the laminate made up of piezoresistive materials is in-between wires on rows and columns.
  • Figure 4 shows that the cylinder magnet 5 generates a magnetic field 5a whose strength is inversely proportional to the distance from magnet.
  • a cylinder has been selected to provide radially uniform magnetic field, such that displacement in by a specific amount any lateral direction will result in a consistent and predictable change in magnetic field at the Hall sensor.
  • Figure 5 demonstrates that the rigid bone structure 4a is magnetized through mounting a magnet 5 so that the layer of bone structure can move with the magnetic to change the local magnetic field 5a in Figure 2. Any pole can be top side or bottom side.
  • the shape of bone structure is not restricted to rectangle.
  • Figure 6, Figure 7 and Figure 8 show how the shape of elastomer is expected to change if there was an external force F applied on the sides and top of bone structure 4a.
  • the magnet 5 moves accordingly because of the deformation of elastomer 2b. Therefore, the local magnetic field 5a can respond to the external force F.
  • the sensing principle of the SA-II layer is based on magnetic flux density measurement
  • GTac of some embodiments incorporate an IMU-based method to reduce the earth magnetic field cancellation.
  • SNR signal-to-noise- ratio
  • SNR signal-to-noise- ratio
  • the earth’s magnetic field is a constant vector (B e ) in the environment, but unknown in the beginning (we can observe its magnetic flux density change via Hall sensor).
  • Figure 9 shows an example application of the force sensor integrated with a robotic gripper 101 to provide the robot a rich contact feedback for improved performance of feedback-based tasks, such as grasping.
  • the tactile sensor 100 can estimate dense normal contact force and tri-axis contact force.
  • the contact surface of 100 may face towards to the contact surface of tactile sensor 100 on another finger to have a compatible grasping contact.
  • the application of this invention includes, but is not limited to, integrating with finger of gripper.
  • FIG. 10 and Figure 11 depict two example applications of this invention utilizing some embodiments of the tactile force sensor.
  • the tactile force sensor 100 is integrated with an upper limb prosthesis/anthropomorphic robotic hand and arm 102 and lower limb prosthesis 103.
  • the tactile sensor 100 can be used to increase the human-robot-interaction safety of upper/lower limb prosthesis by providing feedback of unconscious collision on the arm/shank and grasping stability when manipulating the object to avoid dropping objects.
  • the tactile sensor can output signals from matrix piezoresistive sensor and signals from Flail effect sensor wherein the final output is mixture results of both the two signals.
  • the final mixture signals can be used to infer the joint-level torque on each fingertip since the external contact location and tri-axis force can be estimated from the two signals, respectively.
  • tactile sensing for larger area such as palm of prosthesis/robotic hand 102, prosthesis/robotic arm 102, and prosthesis shank
  • the principle of this invention can be extended.
  • the spatial resolution of matrix piezoresistive sensors and the Flail effect sensors should be adjusted accordingly. While most of the embodiments explained above are with respect to matrix piezoresistive sensor, the same principle may also be applied to develop such tactile force sensor using capacitive sensors, piezoelectric sensors, triboelectric sensors, optical sensors or other similar sensors. Data acquisition and processing
  • Figure 12(a) illustrates a reading-out circuits of matrix piezoresistive sensors.
  • Figure 12(b) illustrates a follower-based signal isolation circuits.
  • Rs is a piezoresistive sensor that has a range of resistance R s in [5k, 100k] ohm, Ro is 10k ohm.
  • R s is a piezoresistive sensor that has a range of resistance R s in [5k, 100k] ohm
  • Ro is 10k ohm.
  • the 4-channel multiplexer is connected to 4 digital I/O pins of Engineering Mega2560. The signals are directly read by 4 analog I/O pins.
  • each GTac can obtain 16 FA-I signals and 3 SA-II signals. Since the Flail sensor in the SA-II layer of GTac sensor measures the global magnetic flux density (MFD), the relative MFD change AB x,y,z may be obtained by subtracting the measured MFD B x,y,z from the g
  • Some embodiments may relate to a two or more fingered gripper, wherein each gripper is provided with a GTac sensor.
  • a threshold Tg is used to control the gripping force exerted by the fingers via feedback from GTac on each fingertip of the gripper.
  • the corresponding motor, rri f of each finger f rotated 1 increment (1 .5 Q ) to drive a rack and pinion gear to conduct finger closure until the leveraged GTac signals gt > T g .
  • Tg high 900
  • Tgi ow 500
  • a 0.3
  • both fingers started closing until gi > Tghigh and g2 > Tg high .
  • both fingers started releasing the object but holding the tweezers until gi ⁇ T gi0w and g2 ⁇ T giow .
  • Tg was set to 700 and a to 0.3.
  • GTac-Gripper A Reconfigurable Under-actuated multi-fingered Robotic Gripper with Tactile Sensing
  • a robotic gripper with a reconfigurable mechanism and tactile sensors (GTac) integrated into the fingers and palm.
  • the gripper may also be referred to as GTac- Gripper.
  • Each finger of the GTac-Gripper may consist of one or more, and presently two, phalanges with a 2 DOF underactuated design and a metacarpophalangeal (MCP) joint.
  • MCP metacarpophalangeal
  • a GTac-Gripper with four adaptive fingers may perform 5 grasping configurations and obtain 228 tactile feedback signals (normal and shear forces) at 150 Hz.
  • the gripper can grasp various everyday objects and achieve in-hand manipulation including translation and rotation with closed-loop control.
  • the gripper achieved a score of 93% (round objects), 0% (flat objects), 78% (tools), 90% (articulated objects), and 65% in total
  • the GTac-Gripper provides a new hardware design and could be beneficial to various robotic applications in the domestic and industrial fields.
  • a 2 DOF linkage-driven underactuated design was adopted for the finger with two phalanges.
  • the underactuated mechanism was constructed by stacking the 4-bar mechanism with the parallelogram mechanism as illustrated in Figure 14(a). Other configurations are possible, are intended to fall within the scope of the present teachings.
  • the actuation link 11 is connected to a servo motor. With the 1 -DOF parallelogram mechanism, the rotation of the active link AB is transmitted to the motion of the link 01 C, which actuates the 2-DOF underactuated four-bar linkage 01CD02.
  • a preloaded torsion spring T in the joint 02 is used to maintain the distal phalanges fully extended.
  • the mechanical stopper kept the distal phalanges aligned under the extension of spring when no external force was applied to the phalanges.
  • Joint OO functioned as the metacarpophalangeal joint of human hands, allowing each finger to change its orientation with respect to the central axis of the palm independently.
  • the trajectory of the fingertip as the finger flexes would be determined by external constraints.
  • Figure 14(b) illustrates the three situations during a finger flexion. In #1 , the contact occurs at the middle phalanx. In #2, two phalanges behave as a rigid body and rotate around a fixed point. In #3, the fingertip moves linearly when the finger is pressed before flexion.
  • Figure 14(c) shows the partial exploded view of a GTac-Gripper. It has 4 fingers and 8 motors, with tactile sensors integrated into the distal phalanx, middle phalanx of the fingers, and the palm. Each finger has one motor for finger flexion/extension and one for reorientation.
  • the soft silicone skin of GTac sensors partially covered the finger surface and provided structural compliance improving grasping stability during object grasping.
  • a workspace analysis is performed to evaluate the manipulation range and dexterity of the GTac-Gripper.
  • the motions of joint 01 and 02 are coupled because of the underactuated finger design.
  • the finger kinematic model was configured as a RRR mechanism and the coordinates were placed for obtaining Denavit-Flartenberg (DH) parameters.
  • DH Denavit-Flartenberg
  • each finger can rotate around joint OO in the XoYo plane by 180°.
  • Link 01 C and link 02D can achieve a motion range of 85° in the Xi Yi plane and 70° in the X2Y2 plane respectively.
  • the DH parameters for the finger were listed in the Table I and can be used by Equation (6) and (7) to obtain the workspace of fingertips.
  • the transformation matrix was defined as
  • the GTac sensors are integrated at appropriate locations to measure contact forces applied by the hand. Presently, those locations are in the distal phalanx and the middle phalanx of each finger and in the palm of the GTac-Gripper, as shown in Figure 15.
  • Each GTac sensor can perceive a plurality of tactile sensing signals, presently 19 tactile sensing signals (16 from the FA-I layer and 3 from the SA-II layer).
  • a GTac-Gripper with 12 GTac sensors, for example, can acquire 228 tactile sensing signals at 150 Hz.
  • a Flail sensor MLX90393 placed at the center of the front is used to acquire the local magnetic flux density and transmit the digital signals - e.g. in I2C bus.
  • Multi-channel operational amplifiers presently four-channel operational amplifiers (MCP6004), are used to acquire analog signals from the piezoresistors.
  • MCP6004 There are four parallel sensing branches for the four fingers of the GTac-Gripper.
  • the uploading multiplexer signals, the downloading digital and analog signals, and power supply (5V) are serially transmitted in each branch.
  • the inter-finger distance between the finger bases are related to the gripper’s stability and grasping/manipulation capabilities in precision grasping (pinch) and caging, especially for underactuated mechanisms.
  • the gripper can continuously control its MCP joints to accomplish different grasping configurations and change the inter-finger distance.
  • FIG 16(a) there are four distinct inter-finger distances, pi, pw, d, and d/2. Five grasping configurations can be achieved with the different inter-finger distances ( Figure 16(b)).
  • the gripper can perform cage grasp (#1 ) for spherical or irregular objects, parallel pinch (#2 and #3) for cylindrical objects or small objects, clasped pose (#4) when the stability of grasping is emphasized, and T-shape grasping (#5) for T- shaped objects such as the drill.
  • GTac-Hand A Robotic Hand with Integrated Biomimetic Tactile Sensing and ECS Recognition Capabilities
  • GTac-Hand may provide 285 tactile measurements.
  • the GTac-Hand can grasp delicate objects and precisely identify their ECSs (extrinsic contact states) via human-like patterning and learning models, which can be used for robots to perform challenging tasks, such as delicate object grasping, object handovers, and ball- hit recognition.
  • GTac-Hand provides (i) tactile sensors with human skin-like normal force (distributed) and shear force (gross) sensing capabilities, and (ii) effective sensory interpretation methods such as those of the human somatosensory system.
  • Figure 17 illustrates a GTac-Hand 1700 and analogizes the structure and operation of the GTac-Hand with a human hand.
  • GTac-Hand 1700 has integrated GTac into the fingers and palm of an anthropomorphic robotic hand that can identify the nine typical ECSs of grasped objects in real time.
  • the GTac-Hand may identify the ECS of a held object via human-like patterning and deep learning models operating on the sensor data generated by the GTac-Hand. Similar to the human sensory-motor controller, the GTac-Hand can perform challenging tasks such as closed-loop grasping and object handovers according to the identified ECS of the grasped object.
  • GTac-Hand integrates electronics for sensing and actuation in the wrist.
  • the sensing PCB may have five 20-pins jump cable connectors for each GTac-finger branch.
  • a microcontroller, Teensy 4.1 is directly connected to the sensing PCB to produce the digital data and functions as a low-level controller of the motors and opens the serial port and CAN bus for communication with the core processing unit.
  • the anthropomorphic hand may be under-actuated and cable-driven as illustrated in Figure 18(d), where 10 rotational joints are actuated by six motors.
  • the shape, size, kinematics, and appearance are similar to those of the human hand.
  • the robotic hand integrates all the electronics and actuation transmissions within the hand.
  • the index, middle, ring, and little fingers have the same design, except for the varied length of the distal section and have two rotational joints, namely proximal interphalangeal joint and metacarpophalangeal joint.
  • the distal and middle phalanges are connected for each finger.
  • the thumb is provided with two degrees of freedom, namely radial abduction/adduction of the carpometacarpal joint and the flexsion/extension of the metacarpophalangeal joint, for obtaining human-like dexterity and mechanical synergies.
  • the GTac-Hand may obtain 285 tactile signals from the fingers and palm.
  • the sensing PCB that can acquire all the signals at 150 Hz.
  • 300 samples may be collected and the mean value of the tail 100 samples ⁇ X , 0.67 s data) may be calculated to initialize GTac signals.
  • the relative values of the tactile signals can be acquired by subtracting the mean values X.
  • a moving average (window size: 6) may be added to reduce the noise of the signals.
  • a filtering algorithm may be implemented to reduce the magnetic disturbance to the SA-II signals of GTac. The signal processing algorithm was only used in the closed-loop grasping phase.
  • the 285 tactile sensing signals consisting of 240 FA-1 type signals and 45 SA-II type signals from 15 GTac units at the n t h sampling moment), and producing tactile events as illustrated in Figure 19.
  • SWFs section-wise features
  • Each convolutional block was assembled by a 3 c 3 convolutional kernel, a rectified linear unit (ReLU), to introduce nonlinearity, and a 2x2 max-pooling layer.
  • the learning rate was 0.001 and batch size as 12 using the Adam optimiser and trained the model for 15 epochs.
  • the QDA-based classifier was implemented using the scikit-learn library that determines the quadratic decision boundary between the classes in the feature spaces based on Bayes’ theorem.
  • the configuration of the QDA model was the default configuration.
  • To verify the supervised learning models we implemented 5-fold cross-validation, wherein the dataset was split into five equal pieces after randomisation, four pieces were used to train the model, and the remaining one was used to validate the trained model. This estimation process was iterated five times.
  • Figure 21 (a) illustrates four phases in the control loop of the GTac-Fland.
  • Figure 21 (b) illustrates Experiment of grasping and handover of an egg using the learned NN-ECS model and the handover controller.
  • Figure 22(a) illustrates an experimental setup of applying ECS identification capabilities to perform ball-hit recognition.
  • Figure 22(b) illustrates recognition results and decoded tactile events representations of one trial experiment.
  • Figure 22(c) illustrates recognition accuracy of all the six trials of ball-hit recognition experiments conducted (96.7% accuracy over 60 trials in total).

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Human Computer Interaction (AREA)
  • Power Engineering (AREA)
  • Force Measurement Appropriate To Specific Purposes (AREA)
  • Manipulator (AREA)
PCT/SG2022/050387 2021-06-29 2022-06-06 Force sensors and devices incorporating force sensors Ceased WO2023277794A2 (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN202280040659.2A CN117501082A (zh) 2021-06-29 2022-06-06 力传感器和包含力传感器的设备
EP22833769.7A EP4363819A4 (en) 2021-06-29 2022-06-06 FORCE SENSORS AND DEVICES INCORPORATING FORCE SENSORS
JP2023580792A JP2024528541A (ja) 2021-06-29 2022-06-06 力センサおよび力センサを組み込んだ装置
US18/286,940 US12510426B2 (en) 2021-06-29 2022-06-06 Force sensors and devices incorporating force sensors

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
SG10202107135Y 2021-06-29
SG10202107135Y 2021-06-29

Publications (2)

Publication Number Publication Date
WO2023277794A2 true WO2023277794A2 (en) 2023-01-05
WO2023277794A3 WO2023277794A3 (en) 2023-02-16

Family

ID=84706531

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SG2022/050387 Ceased WO2023277794A2 (en) 2021-06-29 2022-06-06 Force sensors and devices incorporating force sensors

Country Status (5)

Country Link
US (1) US12510426B2 (cg-RX-API-DMAC7.html)
EP (1) EP4363819A4 (cg-RX-API-DMAC7.html)
JP (1) JP2024528541A (cg-RX-API-DMAC7.html)
CN (1) CN117501082A (cg-RX-API-DMAC7.html)
WO (1) WO2023277794A2 (cg-RX-API-DMAC7.html)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102023117629A1 (de) * 2023-07-04 2025-01-09 Schaeffler Technologies AG & Co. KG Computerimplementiertes Verfahren zum Bereitstellen eines Trainingsdatensatzes, Computerimplementiertes Verfahren zum Trainieren eines KI-Systems und Verwendung eines solchen computerimplementierten Verfahrens, Trainingsdatensatz zum Trainieren eines KI-Systems
WO2025141097A1 (en) * 2023-12-28 2025-07-03 Melexis Technologies Sa Methods and devices for measuring a mechanical force
WO2026006250A3 (en) * 2024-06-24 2026-02-12 Meta Platforms, Inc. Artificial intelligence robotics platform

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2022284790A1 (en) * 2021-05-31 2024-01-18 University Of Kansas Magnetic sensors and methods of making and using thereof
EP4530586A3 (en) * 2021-06-28 2025-06-18 Melexis Technologies SA Force sensor with target on semiconductor package
US12135553B2 (en) 2021-11-30 2024-11-05 Robust AI, Inc. Robotic cart
JP7880124B2 (ja) * 2022-05-20 2026-06-25 株式会社ジャパンディスプレイ 押圧センサ
EP4286812A1 (en) * 2022-06-03 2023-12-06 Melexis Technologies SA A soft force sensor
US20250242500A1 (en) * 2023-04-17 2025-07-31 Figure Ai Inc. Exterior covering system for a humanoid robot
US12650696B2 (en) * 2024-03-01 2026-06-09 Robust AI, Inc. Force multiplying mobile robot
CN120947883A (zh) * 2025-07-09 2025-11-14 武汉华威科智能技术有限公司 一种三维触觉传感器及压力传感测试方法
CN120970882B (zh) * 2025-07-09 2026-04-28 武汉华威科智能技术有限公司 一种触觉传感器及触觉传感器的标定方法
CN122016093A (zh) * 2025-12-17 2026-05-12 成都人形机器人创新中心有限公司 一种视触觉传感器受力检测分析方法
CN122016131B (zh) * 2026-04-14 2026-07-24 悟通感控(北京)科技有限公司 基于法向压力阵列的三维力测量方法及系统

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107003188A (zh) 2014-12-10 2017-08-01 Hci维奥卡尔技术公司 力感测装置
CN110954250A (zh) 2018-12-05 2020-04-03 奇异平台股份有限公司 多轴力量感测器

Family Cites Families (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4876240B2 (ja) 2005-01-28 2012-02-15 国立大学法人 東京大学 触覚センサ及びその製造方法
US7395717B2 (en) * 2006-02-10 2008-07-08 Milliken & Company Flexible capacitive sensor
US7701202B2 (en) * 2006-11-02 2010-04-20 Massachusetts Institute Of Technology Compliant tactile sensor that delivers a force vector
US11389171B2 (en) * 2006-11-21 2022-07-19 David S. Goldsmith Integrated system for the infixion and retrieval of implants
WO2011045837A1 (ja) * 2009-10-14 2011-04-21 国立大学法人東北大学 シート状触覚センサシステム
CN103430000B (zh) * 2011-07-27 2015-06-24 三角力量管理株式会社 力传感器
RU2743044C1 (ru) * 2014-02-20 2021-02-12 Марк ОЛЕЙНИК Роботизированная кухонная система
US10576643B2 (en) * 2014-08-22 2020-03-03 President And Fellows Of Harvard College Sensors for soft robots and soft actuators
CN107249833A (zh) * 2015-01-12 2017-10-13 哈佛学院院长及董事 用于软机器人和软致动器的传感器
US20170086704A1 (en) * 2015-09-25 2017-03-30 Intel Corporation Electronic skin
CN206848977U (zh) * 2016-02-19 2018-01-05 苹果公司 一种电子设备以及用于电子设备的电容式力传感器
JP6703728B2 (ja) * 2016-07-11 2020-06-03 学校法人早稲田大学 近接触覚センサ
US10267690B2 (en) * 2016-09-13 2019-04-23 The Board Of Trustees Of The Leland Stanford Junior University Capacitive force/torque sensor
WO2018175662A1 (en) * 2017-03-21 2018-09-27 University Of Washington Soft shear force resistive sensor embedded in artificial skin
JP7006216B2 (ja) * 2017-12-13 2022-02-10 株式会社ジェイテクト 触知センサ及びアンドロイド
JP6783830B2 (ja) * 2018-08-27 2020-11-11 ミネベアミツミ株式会社 滑りセンサ
WO2020080127A1 (ja) * 2018-10-19 2020-04-23 ソニー株式会社 センサ、積層型センサよび電子機器
CN109443606B (zh) * 2018-12-17 2023-11-03 河北工业大学 一种用于智能机械手的磁致伸缩触觉传感器阵列
GB201910563D0 (en) * 2019-07-24 2019-09-04 Hussein Zakareya Elmo A compliant tri-axial force sensor and method of fabricating the same
DE102019131792B3 (de) * 2019-11-25 2020-12-03 Tacterion Gmbh Greiferbacke mit taktilem Sensor sowie Greifvorrichtung mit einer oder mehreren solcher Greiferbacken
CN111006802B (zh) * 2019-12-17 2021-07-27 华中科技大学 一种多模态可变胞柔性传感器及信号采集系统
CN111397774B (zh) * 2020-01-03 2022-02-15 华中科技大学 一种基于霍尔效应的分布式柔性力位测量装置
US11584026B2 (en) * 2020-02-17 2023-02-21 Toyota Research Institute, Inc. Robot arm assemblies including fingers having deformable sensors
KR20210156501A (ko) * 2020-06-18 2021-12-27 한국과학기술연구원 핑거팁 센서모듈과, 이를 구비한 로봇핸드 및 이를 이용한 파지 방법
JP7264136B2 (ja) * 2020-08-28 2023-04-25 横河電機株式会社 力検出装置、力検出システム及び力検出装置の製造方法
US11565406B2 (en) * 2020-11-23 2023-01-31 Mitsubishi Electric Research Laboratories, Inc. Multi-tentacular soft robotic grippers
US11685058B2 (en) * 2020-11-23 2023-06-27 Mitsubishi Electric Research Laboratories Inc. Soft robotic tentacle gripper
KR20230109752A (ko) * 2020-11-24 2023-07-20 막스-플랑크-게젤샤프트 츄어 푀르더룽 데어 비쎈샤프텐 에.파우. 센서 배열체의 힘 추론을 위한 방법, 네트워크들을 트레이닝하기 위한 방법들, 힘 추론 모듈 및 센서 배열체
US11668554B2 (en) * 2021-03-01 2023-06-06 City University Of Hong Kong Electromechanical sensor and a method of sensing an object or a tactile input using the sensor

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107003188A (zh) 2014-12-10 2017-08-01 Hci维奥卡尔技术公司 力感测装置
CN110954250A (zh) 2018-12-05 2020-04-03 奇异平台股份有限公司 多轴力量感测器

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4363819A4

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102023117629A1 (de) * 2023-07-04 2025-01-09 Schaeffler Technologies AG & Co. KG Computerimplementiertes Verfahren zum Bereitstellen eines Trainingsdatensatzes, Computerimplementiertes Verfahren zum Trainieren eines KI-Systems und Verwendung eines solchen computerimplementierten Verfahrens, Trainingsdatensatz zum Trainieren eines KI-Systems
WO2025141097A1 (en) * 2023-12-28 2025-07-03 Melexis Technologies Sa Methods and devices for measuring a mechanical force
WO2026006250A3 (en) * 2024-06-24 2026-02-12 Meta Platforms, Inc. Artificial intelligence robotics platform

Also Published As

Publication number Publication date
WO2023277794A3 (en) 2023-02-16
JP2024528541A (ja) 2024-07-30
US20240210260A1 (en) 2024-06-27
US12510426B2 (en) 2025-12-30
EP4363819A4 (en) 2025-04-23
EP4363819A2 (en) 2024-05-08
CN117501082A (zh) 2024-02-02

Similar Documents

Publication Publication Date Title
US12510426B2 (en) Force sensors and devices incorporating force sensors
Saudabayev et al. Sensors for robotic hands: A survey of state of the art
Lu et al. GTac: A biomimetic tactile sensor with skin-like heterogeneous force feedback for robots
Cutkosky et al. Force and tactile sensing
Borisov et al. Prototyping of EMG-controlled prosthetic hand with sensory system
JP2024528541A5 (cg-RX-API-DMAC7.html)
Moeinnia et al. Novel Grasping Mechanisms of 3D‐Printed Prosthetic Hands
Sagisaka et al. High-density conformable tactile sensing glove
Thayer et al. Design and implementation of a dexterous anthropomorphic robotic typing (DART) hand
Suthar et al. Robotic Fingers: Advancements, Challenges, and Future Directions–A Comprehensive Review
Khatik et al. On optimal tendon routing-based design of biologically inspired underactuated hand exoskeleton for gross grasping
Ali et al. Development of smart glove system for therapy treatment
Landi et al. Sensorization of soft robot joints for accurate and durable bending measurement
Lee et al. Design of a hand exoskeleton for biomechanical analysis of the stroke hand
Holgado et al. Magnetic 3-axis soft and sensitive fingertip sensors integration for the iCub humanoid robot
Groß et al. Opengrasp-lite version 1.0: A tactile artificial hand with a compliant linkage mechanism
Zecca et al. Experimental analysis of the proprioceptive and exteroceptive sensors of an underactuated prosthetic hand
Castañeda et al. Spatial and temporal analysis of normal and shear forces during grasping, manipulation and social activities
Peerdeman et al. Development of underactuated prosthetic fingers with joint locking and electromyographic control
Malhotra et al. The relationship between actuator reduction and controllability for a robotic hand
Carrozza et al. Design methods for innovative hand prostheses
Chungsangsatiporn et al. A Bio-Inspired Robotic Finger: Mechanics and Control
Johnsson et al. LUCS haptic hand II
Lu A Biomimetic Tactile Sensor With Skin-like Heterogeneous Force Sensing for Robots
Choi et al. Understanding of hands and task characteristics for development of biomimetic robot hands

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 18286940

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 202280040659.2

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22833769

Country of ref document: EP

Kind code of ref document: A2

ENP Entry into the national phase

Ref document number: 2023580792

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2022833769

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022833769

Country of ref document: EP

Effective date: 20240129

WWG Wipo information: grant in national office

Ref document number: 18286940

Country of ref document: US