Adaptive fractal gripper with tactile perception

CN121447664BActive Publication Date: 2026-09-08JIANGNAN UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202511489105.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-10-17
Publication Date
2026-09-08
Estimated Expiration
2045-10-17

AI Technical Summary

Technical Problem

[0003]但是现有的分形夹爪的模式切换机构依赖蜗轮蜗杆和齿轮传动,虽然有自锁功能,一定程度可以增强稳定性,但是这也增加了系统控制的复杂性,而且可能还会导致控制精度不足的问题;此外分形结构虽然能均匀分布力,但是面对极端形状或者微尺度物体时会因为适应性不足影响抓取的成功率;此外,分形结构本身复杂,多级分形会导致制造难度大且维护成本高;并且多级结构的变形需要一定的时间,导致动态抓取效率较低

Benefits of technology

本发明公开了一种具备触觉感知的自适应分形夹爪,通过设计ω形的分形夹爪结构,并且配合X形交叉的夹爪指节提升夹爪在夹取物体时的成功率和加持精度;通过ω形的分形夹爪减少加持物体过程中局部应力集中,使得应力分布更加均匀;并且ω形的分形夹爪通过X形交叉的夹爪指节分散力的传递,ω形的分形夹爪的末端适应变形,X形交叉点弯曲,保证加持过程中稳定性;此外能通过检测压敏导电片的受力情况判断在夹持物体的过程中,分形夹爪是否受到切向力的作用,并通过不断优化夹持策略以保证受力均匀,从而提升夹持的成功率;该分形夹爪还具有结构简单、操作方便、成本较低以及方便维护的优点。此外本发明还将分形夹爪和触觉感知相结合,通过检测分形夹爪上各个位置的受力情况,通过ω形的分形夹爪自适应地缓解夹持的作用力,并且通过检测流经压导电片电流的变化,判断分形夹爪受到作用力的大小并进行自适应调整,实现双重维度上的自适应调整,以实现针对不规则物体、易碎物体和脆弱物体的精准夹取。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121447664B_ABST
    Figure CN121447664B_ABST
Patent Text Reader

Abstract

The application discloses a self-adaptive fractal gripper with tactile perception and belongs to the technical field of intelligent robots. The fractal gripper structure in the shape of omega is designed, and the gripper fingers in the shape of X are crossed to improve the success rate and holding precision of the gripper when the object is gripped. The fractal gripper in the shape of omega reduces local stress concentration during the holding of the object, so that the stress distribution is more uniform. The fractal gripper in the shape of omega disperses the transmission of force through the gripper fingers in the shape of X, the end of the fractal gripper in the shape of omega is adapted to deformation, the X-shaped intersection is bent, and the stability during the holding process is ensured. The fractal gripper also has the advantages of simple structure, convenient operation, low cost and convenient maintenance. In addition, the fractal gripper is combined with tactile perception, the holding force of the fractal gripper is adaptively adjusted by detecting the stress conditions of each position on the fractal gripper, and the accurate gripping of irregular objects, fragile objects and fragile objects is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to an adaptive fractal gripper with tactile sensing capabilities, belonging to the field of intelligent robot technology. Background Technology

[0002] A fractal gripper is a novel robotic end effector based on fractal structures, designed to improve the adaptability and versatility of gripping. It is widely used in industrial automation, medical, 3C electronics, automotive manufacturing, and other fields. Its core principle is based on fractal geometry and mechanical engineering, achieving adaptive gripping through structural design and material selection. Through multiple independent motion units, the fractal gripper can dynamically wrap around objects with few or irregular contact surfaces, such as round tubes and spheres, solving the problem that traditional grippers have difficulty gripping complex shapes. Its segmented flexible structure can apply independent control forces to different parts, avoiding gripping failures due to shape differences. It is especially suitable for irregular objects, fragile items, or flexible materials.

[0003] However, existing fractal gripper mode switching mechanisms rely on worm gears and gear transmissions. Although they have a self-locking function, which can enhance stability to some extent, this also increases the complexity of system control and may lead to insufficient control precision. In addition, although fractal structures can distribute force evenly, their lack of adaptability affects the success rate of gripping when dealing with extreme shapes or micro-scale objects. Furthermore, fractal structures are inherently complex, and multi-level fractals lead to high manufacturing difficulty and maintenance costs. Moreover, the deformation of multi-level structures requires a certain amount of time, resulting in lower dynamic gripping efficiency.

[0004] Therefore, there is an urgent need for a new type of fractal gripper that is simple in structure, easy to operate, and can provide real-time feedback on the force applied to the gripper. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides an adaptive fractal gripper with tactile sensing. This adaptive fractal gripper integrates several adaptive fractal gripper units onto a gripper frame. A pressure sensing layer is disposed above the adaptive fractal gripper. The pressure sensing layers on several adaptive fractal gripper units on the gripper frame are cascaded via wires to form a pressure sensing array. The object is gripped by two adaptive fractal grippers, and tactile sensing is achieved based on the pressure sensing array. The adaptive fractal gripper unit includes a base, gripper joints, a first-level fractal gripper, a second-level fractal gripper, and fractal finger blocks. The base, the first-level fractal gripper, the second-level fractal gripper, and the fractal finger blocks are all connected by gripper joints. The gripper phalanges consist of two straight arms that do not touch each other, arranged in an X-shape. The first-stage fractal gripper has an ω-shaped structure, including two curved support arms and a connecting bridge. The two support arms are symmetrically arranged on both sides of the connecting bridge. The second-stage fractal gripper is exactly the same as the first-stage fractal gripper except for size. The base is fixedly connected to the first-stage fractal gripper via the connecting bridge of the gripper joints. The ends of the two support arms of the first-stage fractal gripper are fixedly connected to the second-stage fractal gripper via the connecting bridge of the gripper joints. The ends of the two support arms of the second-stage fractal gripper are fixedly connected to the fractal finger blocks via the gripper joints. The cross-section of the fractal finger block is an isosceles trapezoid. Furthermore, the base is made of one of polylactic acid, polyglycolic acid, or polycaprolactone. Furthermore, the primary fractal gripper, the secondary fractal gripper, and the gripper knuckles are made of one of thermoplastic polyurethane elastomer, thermoplastic elastomer, or thermoplastic copolyester to ensure that the force on the fractal finger blocks is reduced when gripping objects.

[0006] Furthermore, several adaptive fractal gripper units are fixedly connected to the gripper frame through threaded holes on the base, and a control board is also provided on the gripper frame. A pressure sensing layer is provided at the top of several adaptive fractal gripper units. The pressure sensing layer includes, from bottom to top, a first wire, a first pressure-sensitive conductive sheet, a second wire, a second pressure-sensitive conductive sheet, a third wire, and polydimethylsiloxane. Furthermore, the first and third wires are arranged horizontally to connect several fractal fingers on the same adaptive fractal gripper unit; the second wire is arranged vertically to connect the fractal fingers on adjacent adaptive fractal gripper units. Furthermore, the first and third wires are connected to the control board via longitudinal heat shrink tubing, and several second wires are connected to the control board via transverse heat shrink tubing. Furthermore, the fractal fingers of several adaptive fractal gripper units form a sensor array, which realizes tactile perception of pressure through a control board. Furthermore, the two-stage fractal grippers and gripper phalanges work together to adaptively grip irregular objects; In the ω-shaped structure, the stress generated by the curved support arm when gripping an object is concentrated in the connecting bridge part, and the connecting bridge part transmits the force to the gripper knuckles. The left and right bending of the fractal knuckles relieves the force on the first-level fractal gripper and the second-level fractal gripper when gripping, thereby achieving adaptive adjustment of stress when gripping an object. The fractal grippers and gripper knuckles with an ω-shaped structure are made of materials with high tensile strength and good elasticity. They can undergo slight deformation when gripping objects, thereby dispersing the force generated by the gripping. When gripping irregular objects, the fractal grippers can better conform to the surface of the object, thus ensuring a good gripping effect. The sensor array composed of adaptive fractal grippers can detect the pressure at different points in real time and then feed the pressure back to the control board. The control board judges the force on the fractal grippers based on the feedback pressure information and makes adjustments to ensure that the pressure at each point is consistent. During the clamping process, if the detected pressure is too high or the data collected is too low, the control board will adjust the clamping strategy. First, it will loosen the fractal grippers to reduce their deformation, and then clamp them again. This process is repeated continuously to adjust the clamping posture, thereby ensuring that the pressure on each fractal finger is consistent. This achieves the adaptive adjustment of the control board based on the feedback pressure.

[0007] Furthermore, several first and third conductors are arranged horizontally at uniform intervals, and several second conductors are arranged vertically at uniform intervals. Furthermore, the current is conducted through the transverse heat shrink tubing to the second conductor, then downwards through the first pressure-sensitive conductive sheet and the first conductor, upwards through the second pressure-sensitive conductive sheet and the third conductor, and finally through the longitudinal heat shrink tubing to the control board. Since the pressure received on the first and second pressure-sensitive conductive sheets is different, the magnitude of the current passing through them is also different. By analyzing the magnitude of the current, the magnitude of the pressure can be sensed. Specifically, the magnitude of the pressure on the first and second pressure-sensitive conductive sheets is used to determine whether the adaptive fractal gripper is subjected to a tangential force. When the first and second pressure-sensitive conductive sheets are subjected to the same magnitude of force, the adaptive fractal gripper is not subjected to tangential force and thus can normally grip the object. When the forces acting on the first and second piezoresistive conductive sheets deviate, the resultant force at the same point on the first and second piezoresistive conductive sheets is not perpendicular to the planes on which the first and second piezoresistive conductive sheets are located. This causes the force to deviate further and further from the point of application as it propagates. The current signal generated by this tangential force is transmitted to the control board. The control board controls the adaptive fractal gripper to adjust the gripping posture based on this current signal, thereby avoiding gripping failure caused by the tangential force and ensuring gripping stability.

[0008] Furthermore, the adaptive fractal gripper also combines imitation learning and reinforcement learning algorithms. By continuously learning during the gripping process and adaptively adjusting the gripping posture, the fractal gripper is trained. During the training process, the gripping strategy is continuously optimized, thereby improving the gripping success rate.

[0009] Furthermore, the specific process of combining imitation learning and adaptive fractal grippers is as follows: First, the grasping task is carried out through the teaching mode, and the grasping data is collected during the grasping process; then, the collected data is trained through behavior cloning or inverse reinforcement learning, and the grasping effect is continuously optimized through training; finally, the combination of imitation learning and adaptive fractal grippers is realized. Furthermore, reinforcement learning specifically involves optimizing the gripping strategy of the adaptive fractal gripper through dynamic programming, Q-Learning, or proximal strategy optimization during the execution of the grasping task.

[0010] The beneficial effects of this invention are: This invention discloses an adaptive fractal gripper with tactile sensing. By designing an ω-shaped fractal gripper structure and combining it with X-shaped intersecting gripper knuckles, the success rate and clamping accuracy of the gripper when grasping objects are improved. The ω-shaped fractal gripper reduces local stress concentration during object clamping, resulting in a more uniform stress distribution. Furthermore, the ω-shaped fractal gripper disperses force transmission through the X-shaped intersecting gripper knuckles, and the end of the ω-shaped fractal gripper adapts to deformation, with the X-shaped intersection bending to ensure stability during clamping. In addition, the invention can detect the force on the pressure-sensitive conductive sheet to determine whether the fractal gripper is subjected to tangential force during object clamping, and continuously optimize the clamping strategy to ensure uniform force distribution, thereby improving the clamping success rate. This fractal gripper also has the advantages of simple structure, convenient operation, low cost, and easy maintenance. Furthermore, this invention combines fractal grippers with tactile sensing. By detecting the force at various positions on the fractal grippers, the ω-shaped fractal grippers adaptively alleviate the clamping force. Moreover, by detecting changes in the current flowing through the piezoelectric sheet, the magnitude of the force on the fractal grippers is determined and adaptively adjusted, achieving adaptive adjustment in two dimensions to enable precise gripping of irregular, fragile, and delicate objects. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a three-dimensional structural schematic diagram of an adaptive fractal gripper unit with tactile perception provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the cross-sectional structure of an adaptive fractal gripper unit with tactile sensing provided in Embodiment 2 of the present invention; Figure 3This is a schematic diagram of the end force of an adaptive fractal gripper with tactile sensing provided in Embodiment 2 of the present invention; Figure 4 This is a schematic diagram of the connection relationship between the fractal gripper unit and the control board in an adaptive fractal gripper with tactile perception provided in Embodiment 2 of the present invention; Figure 5 This is a schematic diagram of the fractal gripper tactile matrix in an adaptive fractal gripper with tactile perception provided in Embodiment 2 of the present invention; Figure 6 This is a schematic diagram of a dual-arm robot structure with an adaptive fractal gripper integrating tactile perception, provided in Embodiment 3 of the present invention. Figure 7 This is a schematic diagram of a dual-arm robot with an adaptive fractal gripper integrating tactile perception, provided in Embodiment 3 of the present invention, when holding an object; The components are as follows: 1. Base; 2. Gripper knuckles; 3. Primary fractal gripper; 4. Secondary fractal gripper; 5. Fractal finger block; 6. First conductor; 7. First pressure-sensitive conductive sheet; 8. Second conductor; 9. Second pressure-sensitive conductive sheet; 10. Third conductor; 11. Covering layer; 12. Longitudinal heat shrink tubing; 13. Transverse heat shrink tubing; 14. Control board; 15. Gripper frame; 16. Support arm; 17. Connecting bridge; 18. Base; 19. Moving platform; 20. Support frame; 21. Robotic arm. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0014] Example 1 This embodiment provides an adaptive fractal gripper with tactile sensing. The adaptive fractal gripper integrates several adaptive fractal gripper units onto a gripper frame 15. A pressure sensing layer is provided above the adaptive fractal gripper, and the pressure sensing layers on several adaptive fractal gripper units are cascaded through wires to form a pressure sensing array. The object is clamped by two adaptive fractal grippers, and tactile sensing is achieved based on the pressure sensing array.

[0015] The structure of the adaptive fractal gripper unit is as follows: Figure 1 As shown, it includes a base 1, gripper joints 2, a primary fractal gripper 3, a secondary fractal gripper 4, and fractal finger blocks 5. The base 1 is connected to the primary fractal gripper 3, the primary fractal gripper 3 is connected to the secondary fractal gripper 4, and the secondary fractal gripper 4 is connected to the fractal finger blocks 5 through the gripper joints 2.

[0016] The gripper fingers 2 are two straight arms that do not touch, arranged in an X-shape; the first-stage fractal gripper 3 is an ω-shaped structure, including two curved support arms 16 and a connecting bridge 17. The two support arms 16 are symmetrically arranged on both sides of the connecting bridge 17. The second-stage fractal gripper 4 is completely identical to the first-stage fractal gripper 3 except for size.

[0017] The base 1 is fixedly connected to the connecting bridge 17 of the first-stage fractal gripper 3 via the gripper finger joint 2. The ends of the two support arms 16 of the first-stage fractal gripper 3 are fixedly connected to the connecting bridge 17 of the second-stage fractal gripper 4 via the gripper finger joint 2. The ends of the two support arms 16 of the second-stage fractal gripper 4 are fixedly connected to the fractal finger block 5 via the gripper finger joint 2. The cross section of the fractal finger block 5 is an isosceles trapezoid.

[0018] The base 1 is made of one of polylactic acid, polyglycolic acid, or polycaprolactone. The gripper knuckle 2, the primary fractal gripper 3, and the secondary fractal gripper 4 are made of one of thermoplastic polyurethane elastomer, thermoplastic elastomer, or thermoplastic copolyester to ensure that the force on the fractal finger block 5 is reduced when gripping an object. Several adaptive fractal gripper units are fixedly connected to the gripper frame 15 through threaded holes on the base 1, and a control board 14 is also provided on the gripper frame 15.

[0019] The cross-sectional structure of the adaptive fractal gripper is as follows: Figure 2 As shown, a pressure sensing layer is provided above the fractal finger block 5. The pressure sensing layer includes, from bottom to top, a first wire 6, a first pressure-sensitive conductive sheet 7, a second wire 8, a second pressure-sensitive conductive sheet 9, a third wire 10, and a capping layer 11, wherein the capping layer 11 is polydimethylsiloxane.

[0020] The first wire 6 and the third wire 10 are arranged horizontally to connect several fractal finger blocks 5 on the same adaptive fractal gripper unit; the second wire 8 is arranged vertically to connect fractal finger blocks 5 on adjacent adaptive fractal gripper units.

[0021] like Figure 4 As shown, the first wire 6 and the third wire 10 are connected to the control board 14 via longitudinal heat shrink tubing 12, and several second wires 8 are connected to the control board 14 via transverse heat shrink tubing 13.

[0022] This adaptive fractal gripper unit converts pressure changes into voltage changes at the nodes of fractal finger block 5, calculates resistance values ​​by reading the voltage, and finally senses the force on fractal finger block 5 based on the resistance values.

[0023] The fractal fingers 5 of several adaptive fractal gripper units constitute a sensing array, such as... Figure 5 As shown, tactile pressure is perceived through the control panel 14.

[0024] The primary fractal gripper 3, the secondary fractal gripper 4, and the gripper knuckles 2 work together to adaptively grip irregular objects; In the ω-shaped structure, the stress generated by the bent support arm 16 when gripping an object is concentrated in the connecting bridge 17. The connecting bridge 17 then transmits the force to the gripper knuckles 2. The left and right bending of the fractal knuckles 2 alleviates the force on the first-stage fractal gripper 3 and the second-stage fractal gripper 4 when gripping, thereby achieving adaptive adjustment of stress when gripping an object.

[0025] The materials used in the primary fractal gripper 3, the secondary fractal gripper 4, and the gripper knuckle 2 have high tensile strength and good elasticity, and can undergo slight deformation when the adaptive fractal gripper holds an object, thereby dispersing the force generated by the gripping. When gripping irregular objects, the adaptive fractal gripper can better conform to the surface of the object, thus ensuring a good gripping effect.

[0026] The sensor array composed of adaptive fractal grippers can detect the pressure magnitude at different points in real time, and then feed the pressure back to the control board 14. The control board 14 judges the force on the adaptive fractal grippers based on the feedback pressure information and makes adjustments to ensure that the pressure magnitude at each point is consistent. During the clamping process, if the detected pressure is too high or the data that can be collected is too low, the control board 14 will adjust the clamping strategy. First, it will loosen the fractal grippers to reduce their deformation, and then clamp them again. This process is repeated continuously to adjust the clamping posture, thereby ensuring that the pressure magnitude of each fractal finger block 5 is consistent. Thus, the control board 14 adaptively adjusts the clamping strategy according to the feedback pressure magnitude.

[0027] Several first wires 6 and several third wires 10 are arranged horizontally at uniform intervals. Similarly, several second wires 8 are arranged vertically at uniform intervals. Current is conducted to the second wire 8 through the horizontal heat shrink tubing 13, then downwards through the first pressure-sensitive conductive sheet 7 and the first wire 6, upwards through the second pressure-sensitive conductive sheet 9 and the third wire 10, and finally through the vertical heat shrink tubing 12 to the control board 14. Since the pressure received on the first pressure-sensitive conductive sheet 7 and the second pressure-sensitive conductive sheet 9 is different, the magnitude of the current is also different. The magnitude of the pressure is perceived by analyzing the magnitude of the current. Specifically, the magnitude of the pressure on the first pressure-sensitive conductive sheet 7 and the second pressure-sensitive conductive sheet 9 is used to determine whether the fractal gripper is subjected to a tangential force. Figure 3 As shown: When the first pressure-sensitive conductive sheet 7 and the second pressure-sensitive conductive sheet 9 are subjected to the same magnitude of force, the adaptive fractal gripper is not subjected to tangential force and thus can normally grip the object. When the force applied to the first pressure-sensitive conductive sheet 7 and the second pressure-sensitive conductive sheet 9 is offset, the resultant force on the same point on the first pressure-sensitive conductive sheet 7 and the second pressure-sensitive conductive sheet 9 is not perpendicular to the plane on which the first pressure-sensitive conductive sheet 7 and the second pressure-sensitive conductive sheet 9 are respectively located. This causes the force to deviate further and further from the point of force application as it propagates. The current signal generated by this tangential force is transmitted to the control board 14. The control board 14 controls the fractal gripper to adjust the gripping posture according to the current signal, thereby avoiding gripping failure caused by the tangential force and ensuring gripping stability.

[0028] The primary fractal gripper 3, the secondary fractal gripper 4, and the gripper knuckles 2 work together to adaptively grip irregular objects; In the ω-shaped structure, the stress generated by the bent support arm 16 when gripping an object is concentrated in the connecting bridge 17. The connecting bridge 17 will transmit the force to the gripper phalanges 2. The left and right bending of the gripper phalanges 2 will alleviate the force on the first-stage fractal gripper 3 and the second-stage fractal gripper 4 when gripping, thereby achieving adaptive adjustment of stress when gripping an object. The fractal grippers and gripper knuckles 2 with an ω-shaped structure are made of materials with high tensile strength and good elasticity. They can undergo slight deformation when the fractal grippers hold objects, thereby dispersing the force generated by the gripping. When holding irregular objects, the fractal grippers can better conform to the surface of the object, thus ensuring a good gripping effect. The sensor array composed of adaptive fractal grippers can detect the pressure at different points in real time and then feed the pressure back to the control board. The control board judges the force on the fractal grippers based on the feedback pressure information and makes adjustments to ensure that the pressure at each point is consistent. During the clamping process, if the detected pressure is too high or the data collected is too low, the control board will adjust the clamping strategy. First, it will loosen the fractal grippers to reduce their deformation, and then clamp them again. This process is repeated continuously to adjust the clamping posture, thereby ensuring that the pressure on each fractal finger is consistent. This achieves the adaptive adjustment of the control board based on the feedback pressure.

[0029] This adaptive fractal gripper also combines imitation learning and reinforcement learning algorithms. By continuously learning during the gripping process and adaptively adjusting the gripping posture, the fractal gripper is trained. During the training process, the gripping strategy is continuously optimized, thereby improving the gripping success rate. Among them, imitation learning is behavioral cloning or inverse reinforcement learning; reinforcement learning algorithms are one of dynamic programming, Q-learning, or proximal policy optimization.

[0030] Example 2 This embodiment provides a dual-arm robot equipped with an adaptive fractal gripper featuring tactile sensing, such as... Figure 6As shown, the dual-arm robot includes a base 18, a mobile platform 19, a support frame 20, and a robotic arm 21; The base 18 is mounted on the mobile platform 19 to provide stable support for the robot; several wheels are mounted below the mobile platform 19 to enable flexible movement; the support frame 20 is mounted above the base 18, and any other required components can be integrated on the support frame 20; the robotic arms 21 are mounted on both sides of the top of the support frame 20, and the ends of the robotic arms 21 are provided with fractal grippers as described in Embodiment 2.

[0031] like Figure 7 As shown, when gripping an object, two robotic arms work together to grip irregular objects.

[0032] Some steps in the embodiments of the present invention can be implemented using software, and the corresponding software program can be stored in a readable storage medium, such as an optical disc or a hard disk.

[0033] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An adaptive fractal gripper with tactile sensing capability, characterized in that, The adaptive fractal gripper includes several adaptive fractal gripper units and a gripper frame (15). The several adaptive fractal gripper units are arranged in parallel on the gripper frame (15) and are fixedly connected to the gripper frame (15). The adaptive fractal gripper unit includes, from bottom to top, a base (1), a primary fractal gripper (3), a secondary fractal gripper (4), and a fractal finger block (5); the base (1) and the primary fractal gripper (3), the primary fractal gripper (3) and the secondary fractal gripper (4), and the secondary fractal gripper (4) and the fractal finger block (5) are all fixedly connected by gripper finger joints (2); The gripper phalanges (2) are two straight arms that do not touch each other, and the two straight arms are arranged in an X-shape. The first-order fractal gripper (3) is The structure includes two curved support arms (16) and a connecting bridge (17), the support arms (16) being symmetrically arranged on both sides of the connecting bridge (17); the two support arms (16) of the primary fractal gripper (3) are respectively provided with a secondary fractal gripper (4) at the end of each of the two support arms (16), the secondary fractal gripper (4) being completely identical to the primary fractal gripper (3) except for size; The gripper frame (15) is provided with a longitudinal heat shrink tubing (12), a transverse heat shrink tubing (13), and a control board (14). The adaptive fractal gripper units are also provided with pressure sensing layers. The pressure sensing layers on the adaptive fractal gripper units are interconnected to form a pressure sensing array. The pressure sensing array is connected to the control board (14) through a longitudinal heat shrink tube (12) and a transverse heat shrink tube (13). The adaptive fractal gripper realizes tactile sensing through the pressure sensing array.

2. The adaptive fractal gripper according to claim 1, characterized in that, The pressure sensing layer, from bottom to top, includes a first conductor (6), a first pressure-sensitive conductive sheet (7), a second conductor (8), a second pressure-sensitive conductive sheet (9), a third conductor (10), and a capping layer (11).

3. The adaptive fractal gripper according to claim 2, characterized in that, The first wire (6) and the third wire (10) are arranged horizontally to connect the fractal fingers (5) on the same adaptive fractal gripper unit; the second wire (8) is arranged vertically to connect the fractal fingers (5) on adjacent adaptive fractal gripper units; the first wire (6) and the third wire (10) are connected to the control board (14) through the longitudinal heat shrink tubing (12); the second wire (8) is connected to the control board (14) through the transverse heat shrink tubing (13).

4. The adaptive fractal gripper according to claim 3, characterized in that, The control board (14) senses the pressure on the fractal finger block (5) by detecting the voltage magnitude, and adjusts the clamping strategy according to the pressure magnitude. The current is conducted through the transverse heat shrink tube (13) to the second conductor (8), then downward through the first pressure-sensitive conductive sheet (7) and the first conductor (6), upward through the second pressure-sensitive conductive sheet (9) and the third conductor (10), and finally through the longitudinal heat shrink tube (12) to the control board (14).

5. The adaptive fractal gripper according to claim 4, characterized in that, The adaptive fractal gripper achieves adaptive adjustment of the gripped object through a primary fractal gripper (3), a secondary fractal gripper (4), gripper knuckles (2), and a control plate; in, The stress generated by the curved support arm (16) in the shape structure when gripping an object will be concentrated in the connecting bridge (17) part, and then transmitted to the gripper joint (2) through the connecting bridge (17). The bending of the gripper joint (2) will relieve the force on the first-stage fractal gripper (3) and the second-stage fractal gripper (4) when gripping the object, thereby realizing the adaptive adjustment of stress. The control board (14) adjusts the clamping strategy in real time according to the feedback pressure to ensure that the pressure at each point is consistent, thereby realizing adaptive adjustment based on the clamping strategy of the control board (14).

6. The adaptive fractal gripper according to claim 5, characterized in that, The control board (14) determines whether the adaptive fractal gripper is subjected to tangential force by judging the magnitude of the pressure on the first pressure-sensitive conductive sheet (7) and the second pressure-sensitive conductive sheet (9). When the first pressure-sensitive conductive sheet (7) and the second pressure-sensitive conductive sheet (9) are subjected to the same magnitude of force, the adaptive fractal gripper is not subjected to tangential force and thus clamps the object normally. When the force applied to the first pressure-sensitive conductive sheet (7) and the second pressure-sensitive conductive sheet (9) is offset, the resultant force on the same point on the first pressure-sensitive conductive sheet (7) and the second pressure-sensitive conductive sheet (9) is not perpendicular to the plane on which the first pressure-sensitive conductive sheet (7) and the second pressure-sensitive conductive sheet (9) are located, causing the force transmission to deviate from the point of force application. The current signal generated by this tangential force will be transmitted to the control board (14). The control board (14) controls the adaptive fractal gripper to adjust the gripping posture according to the current signal, thereby avoiding gripping failure caused by the tangential force.

7. The adaptive fractal gripper according to claim 6, characterized in that, The adaptive fractal gripper optimizes the gripping strategy during the gripping process by combining imitation learning and reinforcement learning algorithms.

8. The adaptive fractal gripper according to claim 7, characterized in that, The base (1) is made of polylactic acid, polyhydroxyacetic acid or polycaprolactone; The first-stage fractal gripper (3), the second-stage fractal gripper (4), and the gripper knuckle (2) in the adaptive fractal gripper are made of one of thermoplastic polyurethane elastomer, thermoplastic elastomer, or thermoplastic copolyester. The imitation learning mentioned is either behavioral cloning or inverse reinforcement learning; The reinforcement learning algorithm is one of dynamic programming, Q-Learning, or proximal policy optimization.

Citation Information

Patent Citations

  • Fractal structural body and fractal self-adaptive grabbing dual-mode clamping jaw

    CN117754617A

  • Electric clamping jaw

    CN118123883A