22 results about "All fingers" patented technology

The invention relates to the technical field of robots, and discloses a dexterous hand adaptive control method and device for multi-agent collaborative reinforcement learning, and the method comprises the steps: constructing a simulation environment comprising a multi-degree-of-freedom bionic dexterous hand and a target object through a physical engine; on the basis of multi-finger cooperative kinematics characteristics of the bionic dexterous hand, a linkage rule used for constraining actions of all fingers is generated; configuring each finger as an independent agent, constraining each finger action by adopting a multi-agent near-end strategy optimization algorithm in combination with a linkage rule, and training a multi-finger collaborative grabbing strategy model; and the trained collaborative grabbing strategy model is deployed to an entity bionic dexterous hand control system, a control instruction is generated by collecting sensor data in real time, and the bionic dexterous hand is driven to execute self-adaptive grabbing operation according to the control instruction. Multi-finger cooperative self-adaptive grabbing of the bionic dexterous hand can be achieved, and the precision and stability of grabbing in a high-degree-of-freedom scene and the adaptability to the dynamic environment are improved.

This application discloses a hand function rehabilitation evaluation system and method. The system includes a hand evaluator and a main controller. The hand evaluator collects a first video signal of a patient's palm completing a first specified test process. The main controller obtains a first characteristic parameter according to the first video signal, compares it with a corresponding first target parameter value, and obtains a hand function rehabilitation evaluation result. Among them, the first specified test includes the palm moving from a closed state to an open state, or the palm moving from an open state to a closed state. The first characteristic parameter includes the extended length of each finger, and the time interval between when the extended lengths of all fingers reach the maximum reference value and when the extended lengths of all fingers reach the minimum reference value. In the embodiments of this application, the hand evaluator can collect the video signal of the patient's palm completing the specified test process in real time, process these signals in a timely manner and extract characteristic parameters, so as to quickly obtain the hand function rehabilitation evaluation result. Through precise comparison, the evaluation result is more objective and accurate.

The present application relates to a combined UV nail lamp having clips. Clips are combined with UV lamp modules. In the present application, the UV lamp modules are fixed on all fingers by means of the clips, so that the UV lamp modules can accurately irradiate nails, thereby achieving a faster curing effect. The UV lamp modules on the fingers all can be located above the nails and remain stable, thereby achieving accurate irradiation positions.

The utility model relates to a glove, in particular to a glove of wearable equipment. The forefinger fixing part extends along the forefinger direction of the hand back part, the wrist strap extends along the side edge of a palm, the trigger device is arranged on the forefinger fixing part, the clamping part is arranged on the surface of the hand back part, and an electronic device can be clamped above the clamping part. The upper end edge of the outer periphery of the hand back part inclines from the index finger to the little finger and covers the roots of other parts or all fingers except the thumb, and the side edge of the little finger is connected with the wrist strap and forms an included angle with the longitudinal axis Y; the wrist strap extends towards the wrist back area and forms an included angle with the transverse axis X. The structure can prevent the edge warping problem caused by the fact that the glove is not provided with the palm part. No palm portion is arranged, abrasion of the palm portion and foreign body sensation during wearing are reduced, the length-width proportion of the hand back portion is similar to the shape of the hand back of a human body, and wearing is more comfortable. The whole glove is similar to a plane structure, is small in thickness and is easy to store and store.

The present invention discloses a reconfigurable rigid-flexible transformation manipulator based on belt drive and its deformation method, comprising a base, at least three rigid-flexible transformation fingers, and a finger grasping drive mechanism; each rigid-flexible transformation finger comprises a finger body, a rigid-flexible transformation mechanism, and a belt transmission mechanism; the fingertip of the finger body comprises two connecting rod mechanisms arranged symmetrically in the upper and lower parts; each connecting rod mechanism comprises a support connecting rod and a retracting connecting rod that are hinged to each other; the rigid-flexible transformation mechanism is arranged on the symmetry axis of the two connecting rod mechanisms and is connected to the two retracting connecting rods, and can retract the two retracting connecting rods inward or unfold them outward to a straight state; the belt transmission mechanism comprises a belt wrapped around the outer periphery of the fingertip; and the finger grasping drive mechanism can drive the expansion or contraction of all finger bases. The present invention can combine the advantages of rigid manipulators and flexible manipulators, can realize the position change of the grasped object, and has the characteristics of low manufacturing cost and strong task adaptability.

A grasping device for an object comprising a platform (10) with longitudinal axis (X) and six fingers (13, 14) articulated for rotation on the platform (10), and grasping means carried by each of the free ends of the fingers (13, 14), the at least three fingers (13, 14) being regularly articulated angularly around the longitudinal axis (X), each finger (13, 14) comprising a double parallelogram linkage including a first parallelogram (P1) articulated on the platform (10) about an axis orthogonal to the longitudinal axis (X), a second parallelogram (P2) being articulated on the first parallelogram (P1), and a set of gears between the first parallelogram (P1) and the second parallelogram (P2), such that the movement in one direction of rotation of the first parallelogram (P1) imposes a movement in the opposite direction of rotation of the second parallelogram. (P2),and an actuator (A1) carried by the platform and configured to move all the fingers (13, 14) simultaneously. [Fig.2]

A watch receiving glove method and assembly includes a hand covering for covering all fingers, a palm, and a back side of a hand. The hand covering includes at least one finger sleeve and a hand opening for receiving the hand. A wrist covering is attached to and is coextensive with a perimeter edge of the hand opening. The wrist covering comprises a tube for receiving and extending around a wrist of the hand. The tube has a distal edge with respect to the hand covering. The wrist covering includes an upper section is positionable on an upper side of the wrist and lower section is positionable on a bottom side of the wrist. The wrist covering has a display opening extending therethrough. A display case is positionable in the display opening when a strap attached to the display case is extended around the wrist.

The invention discloses a humanoid dexterous hand and a humanoid robot adopting the humanoid dexterous hand. According to the humanoid dexterous hand, a finger driving mechanism comprises at least one finger driving motor layer, a plurality of finger driving motors are arranged in each finger driving motor layer, each finger driving motor is connected with a finger joint of a corresponding hand assembly through a traction rope, and the number of the finger driving motors in each finger driving motor layer is smaller than or equal to 4; the output shafts of all the finger driving motors are arranged outwards, and the projections of the output shafts in the plane perpendicular to the length direction of the arm assembly do not coincide. The invention further discloses a humanoid robot which adopts the humanoid dexterous hand of any scheme. The robot arm has the advantages that mutual friction, winding and even cutting caused by path crossing and contact of a plurality of traction ropes in a narrow space are avoided, and the overall shape of the robot arm is closer to the thickness of a real human arm.

To provide a durable and simply constructed work hand protection device that can safely protect the back and palm of the hand. [Solution] This work hand protection device has three sets of openings: a first finger opening for inserting the thumb, a second finger opening for inserting all fingers other than the thumb, and a wrist opening for inserting the wrist, and covers the back and palm sides of the worker's hand to protect the worker's hand. The device has a cushioning material built in and is a rectangular protective body of a predetermined length that is bent in a U shape from the back of the hand to the palm side via the knife part of the worker's hand. It consists of a first connecting member located on the wrist opening side of the protective body and detachably connecting the open ends of the protective body, and a second connecting member located on the second finger opening side of the protective body and elastically connecting the open ends of the protective body, with the opening between the first and second connecting members being the first finger opening for inserting the thumb.

The invention provides an intelligent learning and two-stage reinforcement learning training method based on standard gesture guidance. The intelligent learning method comprises the following steps: establishing a mapping algorithm from preset standard gesture knowledge to a reinforcement learning action space, and converting joint angle data of a preset standard grabbing gesture into a target guide signal which can be recognized by reinforcement learning through the mapping algorithm; the joint angle difference of the current finger action of the intelligent body is monitored in real time, and when all the finger joint angle differences controlled by the intelligent body strategy reach the preset posture approaching threshold value, the guiding mode is automatically switched to the exploration mode for intelligent body training. Through the preset gesture guiding mechanism, blindness of traditional random exploration is avoided, the training interaction frequency is reduced, and the calculation cost and the training time are reduced. A self-adaptive switching mechanism of guiding to an exploration mode is adopted, smooth transition from imitation learning to autonomous innovation is achieved, the problem of insufficient innovation ability caused by excessive constraint is avoided, and the efficient learning convergence speed is kept.

The utility model discloses a wrist, palm and finger fixing typewriting auxiliary device for a hand dysfunction patient, which comprises an auxiliary brace, the auxiliary brace comprises a fabric binding part and a support rib, the wrist, palm and finger parts of a human body are sleeved in the fabric binding part, and the support rib is arranged on the wrist, palm and finger parts of the human body. The plurality of supporting ribs are arranged in the fabric binding part and are used for performing auxiliary supporting on the human hand part sleeved in the fabric binding part; other fingers except the index finger of a human hand extend out of the fabric binding part, and at least one group of binding components which are used for binding the index finger, the wrist and the palm and can be adjusted in tightness are arranged on the fabric binding part corresponding to the index finger, the wrist and the palm. The two supporting ribs are arranged on the inner side of the wrist portion of the fabric binding portion and are designed to enable the wrist joint to slightly stretch out of the back. According to the utility model, an affected hand is driven to move through upper limb movement and gravity action, so that the actions of independently knocking a keyboard by an index finger, touching by the index finger, sliding a screen and sliding a mouse are realized, and a patient is assisted to independently use an electronic product without relying on other people.

The present invention discloses a grip-adaptive underactuated hand exoskeleton mechanism from base to tip and the underactuated linkage mechanism therein. The hand exoskeleton mechanism comprises: an underactuated linkage mechanism and a back-of-hand base plate, a pipeline mechanism driving the underactuated linkage mechanism, and a drive motor group installed at the distal end. The distal end of the underactuated linkage mechanism is bound to the distal end of the finger, and the motor group drives the pipeline mechanism and is assisted by a return spring installed on the linkage mechanism to achieve active flexion / extension of all fingers and active abduction / adduction of the thumb. The underactuated linkage mechanism and the fingers together form a multi-degree-of-freedom mechanism that can automatically adapt to different finger sizes and the different sizes and shapes of grasped objects. The self-adaptive gripping underactuated hand exoskeleton mechanism described in the present invention is mainly used for rehabilitation training of finger function in hemiplegic patients after stroke and to assist finger movement in daily life for patients who cannot recover.

A rehabilitation training glove for a hemiplegic patient comprises a palm part, the left side of the palm part is fixedly connected with five sets of finger cots, the outer side of the palm part is provided with a flexion and extension training assembly, the flexion and extension training assembly comprises a lower frame and an upper frame, and the lower frame and the upper frame are slidably connected to the outer side of the palm part; the lower frame is rotationally connected with the upper frame through a hinge, and the left sides of the lower frame and the upper frame are fixedly connected with clamping rods corresponding to the finger sleeves respectively. By arranging the flexion and extension training assembly, a driving motor drives a screw rod to rotate, then movement of an upper frame and a lower frame is controlled, accurate control over the positions of clamping rods is achieved, fingers are guided to conduct ordered flexion and extension training, all fingers of a hemiplegic patient can be trained at the same time, the training comprehensiveness and efficiency are improved, and the training efficiency is improved. The continuous flexion and extension training is beneficial to enhancing the strength and flexibility of finger muscles, promoting blood circulation and accelerating the recovery of neurological functions.

The application discloses a palm capable of fixed-axis grabbing based on a metamorphic structure, and the palm is a closed chain structure which is formed by a first rod, a second rod, a third rod, a fourth rod and a fifth rod through a hinge in sequence to form a spherical five-link mechanism; a hinge is used between two adjacent links, and the hinge rotation axis passes through the spherical center of the spherical five-link mechanism; the fifth rod is connected with an external base, and the spherical five-link mechanism contains two degrees of freedom; a rotating finger base is arranged on the second rod, the third rod and the fourth rod, and the rotating axis of the rotating finger base passes through the spherical center of the spherical five-link mechanism; the finger bending direction of all the finger bases always coincides with an axis; the grabbing surface of all the fingers always passes through the spherical center when the palm is deformed, so that the pinch, grab, twist and hold postures are realized, and the action of grabbing columnar objects with different diameters is realized.

The invention relates to a dental floss applicator 2 in the form of a closed loop 4 made from a section 7 of dental floss 6, which is connected to itself at its ends to form the loop 4. The closed loop design 4 allows the user to use the dental floss 6 more easily without having to wrap it around individual fingers. The user can tighten the loop 4 with several or all fingers and, for example, gently insert it into the interdental spaces with their index fingers or thumbs, easily placing a piece of unused dental floss 6 for each tooth.

To provide a finger movement tool having variety even though a structure is simple.SOLUTION: A finger movement tool forms a substantially dish shape, has elasticity, has a size of palm size that can be gripped with other fingers than a thumb facing the thumb, enables bending movement with all fingers or the thumb and each finger, and can be used by being carried at the time of walking. By tapping Arabic numbers provided in a substantially-dish-shaped surface part with a finger, addition, subtraction, multiplication and division by the mental arithmetic method can be performed, and this has an effect of brain training and body training.SELECTED DRAWING: Figure 1

The invention discloses a dexterous hand multi-mode perception and control method, system and device and a medium, and relates to the field of dexterous hand multi-mode perception and control, and the method comprises the steps: obtaining original tactile data and original visual data corresponding to each finger; performing data compression and semantic fusion on the original tactile data and the original visual data to obtain a fusion feature vector corresponding to each finger; inputting the fusion feature vector corresponding to each finger into a finger-level KAN subnet corresponding to the finger to obtain a motor torque suggestion value; inputting the intermediate layer features of the finger-level KAN subnet into a global collaborative KAN network, and predicting to obtain a torque correction coefficient set; the torque correction coefficient set comprises torque correction coefficients of all joints of all fingers; and the motor torque value and the torque correction coefficient of each joint of each finger are used for performing multi-finger cooperative control on the dexterous hand. According to the invention, high-precision and high-adaptability control of the dexterous hand is realized.

The invention discloses a negative pressure suction cup dexterous hand used for grabbing flexible materials and a grabbing method, the dexterous hand comprises a base and three fingers evenly distributed in the circumferential direction, each finger is formed by sequentially hinging a far finger end, a middle finger end and a near finger end, and each joint is driven by an independent motor to achieve pitching or swinging motion. The finger pulp of the far finger end is provided with an array type negative pressure suction cup, the finger back is provided with an independent air path connector, the suction cups of all the fingers are connected in parallel through air pipes and then connected to a shared negative pressure adjusting valve and a vacuum source, and unified adjustment of air pressure is achieved. The suction cup can be attached to a complex curved surface in a self-adaptive mode by independently controlling all fingers and all knuckles to move; the negative pressure of the suction cups is adjusted on the basis of the material of the cloth, and efficient and lossless separation of single layers in the stacked cloth can be achieved; and after separation, the fingers can be cooperatively folded to form wrapping type stable grasping of the cloth. The problems that the flexible thin-layer material is difficult to separate and unstable to grab in the automatic grabbing process are solved.

The utility model relates to the technical field of medical instruments, and provides a hand function recovery grip strength training device which comprises a hand-muscle developer body, a hand-muscle developer base is arranged at the bottom of the hand-muscle developer body, and a grip strength training insertion hole is formed in the hand-muscle developer body. A sliding bin is formed in the position, located in the hand-muscle developer base, of the lower portion of the grip strength training inserting hole, a grip strength extrusion block is connected into the sliding bin in an inserted mode, and an upper induction bin is formed in the position, located below the hand-muscle developer base, of the bottom of the grip strength extrusion block; by means of the upper induction bin, when the opening and closing mechanism at the bottom is closed, a user can hold, grasp and press the grip strength extrusion block to extrude the sliding bin, air in the upper induction bin is detected through the upper induction bin, and different grip strength values formed by all fingers can be detected.

The invention discloses a humanoid dexterous hand and a humanoid robot adopting the humanoid dexterous hand. According to the humanoid dexterous hand, an arm assembly comprises a finger driving mechanism and a wrist driving mechanism, the finger driving mechanism comprises at least two sections of driving assemblies, and the diameter of the section of driving assembly close to a hand assembly is larger than that of the section of driving assembly relatively far away from the hand assembly; each section of driving assembly is provided with at least one finger driving motor layer provided with at least one finger driving motor; the output shafts of all the finger driving motors are arranged outwards, and the projections of the output shafts in the plane perpendicular to the length direction of the arm assembly do not coincide. The invention further discloses a humanoid robot which adopts the humanoid dexterous hand of any scheme. The robot arm has the advantages that mutual friction, winding and even cutting caused by path crossing and contact of a plurality of traction ropes in a narrow space are avoided, and the overall shape of the robot arm is closer to the thickness of a real human arm.

The application discloses a dexterous hand multi-modal perception and control method, system, device and medium, relates to the field of dexterous hand multi-modal perception and control, and comprises the following steps: acquiring original tactile data and original visual data corresponding to each finger; performing data compression and semantic fusion on the original tactile data and the original visual data to obtain a fusion feature vector corresponding to each finger; inputting the fusion feature vector corresponding to each finger into a finger-level KAN subnet corresponding to the finger to obtain a motor torque suggestion value; inputting an intermediate layer feature of the finger-level KAN subnet into a global collaborative KAN network to obtain a torque correction coefficient set; the torque correction coefficient set comprises torque correction coefficients of all joints of the fingers; and the motor torque value of each joint of each finger and the torque correction coefficient are used for multi-finger collaborative control of the dexterous hand, so that high-precision and high-adaptability control of the dexterous hand is realized.

This utility model relates to the field of finger machining technology, and more particularly to a tooling for drilling holes in parts, aiming to solve the problem of low efficiency in clamping and removing fingers in existing drilling tooling. This utility model includes a base plate, side limiting plates, and a pressure plate; the base plate is used to contact the bottom surface of the finger; the side limiting plates have multiple side limiting holes for contacting the sides of the finger, into which the finger is inserted; the pressure plate is used to contact the top surface of the finger; the base plate, side limiting plates, and pressure plate are detachably connected, and the side limiting plates are configured to move towards the base plate to disengage the finger from the side limiting holes. When clamping the finger, simply connecting the base plate, side limiting plates, and pressure plate is sufficient to fix all fingers, eliminating the need to fix each finger individually, greatly reducing the clamping workload. During disassembly, simply removing the pressure plate and moving the side limiting plates downwards allows the finger to disengage from the side limiting holes, eliminating the need to remove each finger individually, greatly improving removal efficiency.