Bionic manipulator based on human skeleton simulation

Abstract

The application discloses a kind of bionic manipulator based on human skeleton simulation, it is related to manipulator technical field, including the manipulator of base, and manipulator is composed of mechanical arm and mechanical arm, and is provided with bionic component at the end of manipulator, through upper arm and forearm simulate human arm skeleton, and set up in base on the avoidance component, through 3D depth camera, the avoidance action of manipulator and bionic component, provide visual monitoring condition.The application takes manipulator as the basis of large space and long distance travel adjustment, simulates the multi-dimension and large amplitude action scene generated by human body skeleton, synchronously collocates the small space and close distance hand bionic scene simulated by upper arm, forearm and palm finger joint assembly, both, not only satisfy the demand of long distance product's grabbing, but also can realize the grabbing transport effect of product under the working condition of close distance, small volume, irregular, soft texture.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical hands, in particular to a bionic mechanical hand based on human skeleton simulation. BACKGROUND

[0002] A mechanical hand is an automatic operating device that can imitate the functions of human hands and arms to grab, carry objects or operate tools according to fixed programs. It has the advantages of both human hands and mechanical devices in structure and performance. Multi-joint mechanical hands have the advantages of flexible movement, small inertia, and strong versatility, and can grab workpieces close to the machine base and work around obstacles between the machine body and the working machine.

[0003] In the process of grabbing and transporting products, traditional industrial mechanical hands are usually used. If the product is small in size, the industrial mechanical hand is limited in grabbing and positioning, and cannot form an effective gripping shape. If the product is irregular in shape, the industrial mechanical hand is unstable in grabbing and positioning, and is prone to product dropping and damage. If the product is soft in texture, it is prone to damage and deformation. In the face of the above working conditions, the traditional industrial mechanical hand is greatly limited and needs to be replaced with different tooling fixtures, which is not flexible and variable. SUMMARY

[0004] This section aims to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, abstract and title, and such simplifications or omissions cannot be used to limit the scope of the present application.

[0005] In view of the above and / or existing problems in the bionic mechanical hand based on human skeleton simulation, the present application is proposed.

[0006] Therefore, the problem to be solved by the present application is how to solve the problem that the traditional industrial mechanical hand is greatly limited and not flexible and variable in multi-working-condition scenarios.

[0007] To solve the above technical problems, the present application provides the following technical scheme: a bionic mechanical hand based on human skeleton simulation, comprising a mechanical hand with a base, the mechanical hand being composed of a mechanical large arm and a mechanical small arm, and a bionic assembly being provided at the end of the mechanical hand, the human arm skeleton being simulated through the upper arm and forearm, and an avoidance assembly being provided on the base, the avoidance action of the mechanical hand and the bionic assembly being monitored visually through a 3D depth camera.

[0008] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the manipulator further comprises a rotating table rotating on the base through a rotating motor, and the rotating table and the large arm are connected through a large arm motor.

[0009] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the large arm and the small arm are connected through a small arm motor, the small arm and the bionic assembly are connected through an end motor, and the outside of the end motor is fixed with a steering motor through a connecting piece.

[0010] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the bionic assembly further comprises a shoulder steering gear fixed at the outside of the steering motor, the upper arm is connected through the shoulder steering gear, and the upper arm and the forearm are connected through an elbow joint steering gear.

[0011] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the outside of the forearm is provided with a palm and finger joint assembly, and the forearm and the palm and finger joint assembly are connected through a wrist steering gear I and a wrist steering gear II.

[0012] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the joints of the palm and finger joint assembly are embedded with micro steering gears, and a sensing data glove is sleeved on the outside of the palm and finger joint assembly.

[0013] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the forearm is respectively embedded with a bending sensor module and a posture sensor module, and the bending sensor module and the posture sensor module are connected through the sensing data glove to monitor the palm and finger joint assembly.

[0014] As a preferred scheme of the bionic manipulator based on human skeleton simulation, a micro infrared sensor is embedded in the palm of the palm and finger joint assembly, and a micro pressure sensor is embedded in the inside of the finger joint of the palm and finger joint assembly; a circular opening is reserved on the side of the sensing data glove close to the micro infrared sensor, and the opening diameter of the circular opening is greater than the lens diameter of the micro infrared sensor.

[0015] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the avoiding assembly further comprises an angle motor embedded on the outside of the rotating table, and the output shaft of the angle motor is fixed with a 3D depth camera; the periphery of the base is fixed with a 3D laser radar through a vertical rod.

[0016] As a preferred scheme of the bionic manipulator based on human skeleton simulation, the outer side of the mechanical arm and the mechanical arm is fixed with a capacitive proximity sensor, and the inner side of the arm motor, the arm motor and the end motor is provided with a joint torque sensor; the forearm is embedded with a wrist six-dimensional force sensor.

[0017] The bionic manipulator based on human skeleton simulation has the advantages that: the manipulator is used as a basis for large space and long distance travel adjustment, a multi-dimensional and large amplitude action scene generated by simulation of human body skeleton is simulated, a small space and a short distance hand bionic scene simulated by the upper arm, forearm and palm joint assembly is matched synchronously, the two are combined, not only the long distance product grabbing demand is met, but also the product grabbing and transportation effect under the conditions of short distance, small volume, irregularity and soft texture is realized, the problem that the traditional industrial manipulator is limited and needs to be replaced by different tooling fixtures is solved, the bionic manipulator is flexible and variable, has high degree of freedom, and has a safety function of active avoidance, a simulation state of human body squatting and curling is formed, the fence type passive protection operation of the traditional industrial manipulator is replaced, and active avoidance safety measures are provided for personnel and vehicles that mistakenly enter the action space. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 Working scene of the bionic manipulator based on human skeleton simulation Figure 1 .

[0020] Figure 2 Working scene of the bionic manipulator based on human skeleton simulation Figure 2 .

[0021] Figure 3 Working scene of the bionic manipulator based on human skeleton simulation Figure 3 .

[0022] Figure 4 Avoidance scene diagram of the bionic manipulator based on human skeleton simulation.

[0023] Figure 5 Partial exploded view of the bionic assembly of the bionic manipulator based on human skeleton simulation.

[0024] Figure 6 Partial cross-sectional view of the forearm and palm joint assembly of the bionic manipulator based on human skeleton simulation.

[0025] Figure 7 This is a magnified view from below of the hand and finger joint assembly of a bionic robotic hand based on human skeletal simulation.

[0026] In the diagram: 1. Base; 2. Protective sleeve; 3. Robotic arm; 31. Rotary motor; 32. Rotary table; 33. Robotic upper arm; 34. Upper arm motor; 35. Robotic forearm; 36. Forearm motor; 37. Steering motor; 38. End motor; 41. Shoulder servo; 42. Upper arm; 43. Elbow joint servo; 44. Forearm; 45. Hand and finger joint assembly; 46. Sensor data glove; 5. Wrist servo one; 6. Wrist servo two; 7. Miniature servo; 8. Bending sensor module; 9. Attitude sensor module; 10. Miniature infrared sensor; 11. Miniature pressure sensor; 121. Angle motor; 122. 3D depth camera; 123. 3D LiDAR; 124. Capacitive proximity sensor; 125. Joint torque sensor; 126. Wrist six-dimensional force sensor. Detailed Implementation

[0027] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0028] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0029] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0030] Example 1, referring to Figures 1-7 This is the first embodiment of the present invention. This embodiment provides a bionic robotic hand based on human skeleton simulation, including a robotic hand 3 with a base 1. The robotic hand 3 is composed of a robotic upper arm 33 and a robotic forearm 35, and is protected by a protective sleeve 2. The protective sleeve 2 is made of a highly elastic and tear-resistant composite fabric. The robotic hand 3 serves as the basis for large-space and long-distance stroke adjustment, simulating the multi-dimensional and large-amplitude movement scenarios generated by the human body skeleton, and meeting the grasping needs of long-distance products.

[0031] Specifically, it also includes a rotating platform 32 that is rotated on the base 1 by a rotating motor 31. With the base 1 as a solid support, the rotating motor 31 drives the mechanical arm 33 and the mechanical arm 35 on the rotating platform 32 and the whole to rotate and switch horizontally to meet the product grasping and transportation needs in different spatial orientations.

[0032] Furthermore, the rotary table 32 and the mechanical arm 33 are connected by the arm motor 34. With the rotary table 32 as a fixed support, the arm motor 34 drives the mechanical arm 33 and the mechanical forearm 35 and the whole to perform multi-directional rotation adjustment in the vertical direction.

[0033] The mechanical boom 33 and the mechanical forearm 35 are driven by the forearm motor 36. With the mechanical boom 33 as a fixed support, the forearm motor 36 drives the entire upper part to perform multi-directional rotation adjustment in the vertical direction. Combined with the horizontal rotation switching of the turntable 32 and the multi-directional vertical rotation adjustment of the mechanical boom 33 and the mechanical forearm 35, a large space and multi-dimensional motion stroke are formed to meet the product grasping and transportation needs at both long and short distances.

[0034] Furthermore, the mechanical arm 35 and the bionic component are connected by an end motor 38. A steering motor 37 is fixed to the outside of the end motor 38 through a connector. With the mechanical arm 35 as a fixed support, the end motor 38 drives the entire component to perform multi-directional rotation adjustment in the vertical direction, and the steering motor 37 drives the entire component to rotate and switch again in the horizontal direction, further increasing the product's gripping and transportation range.

[0035] A bionic component is set at the end of the robotic arm 3. The upper arm 42 and forearm 44 simulate the human arm skeleton. Combined with the hand and finger joint assembly 45, which simulates a small space and close-range hand bionic scene, the product grasping and transportation effect is achieved under working conditions such as close distance, small volume, irregular shape, and soft texture.

[0036] Specifically, it also includes a shoulder servo motor 41 fixed to the outer end of the steering motor 37, and the upper arm 42 is driven by the shoulder servo motor 41. With the steering motor 37 as the base, the shoulder servo motor 41 drives the upper arm 42, forearm 44 and palm finger joint assembly 45 to perform multi-angle adjustments to simulate the overall movement of the hand in the human shoulder scenario.

[0037] For example, the shoulder servo motor 41 drives the upper arm 42, forearm 44 and palm finger joint assembly 45 to extend outward as a whole, simulating the overall outward movement of the human hand. The shoulder servo motor 41 drives the upper arm 42, forearm 44 and palm finger joint assembly 45 to move inward as a whole, simulating the overall inward movement of the human hand, thus meeting the product grasping and transportation needs under different spatial position conditions.

[0038] The upper arm 42 and the forearm 44 are connected by an elbow joint servo motor 43. With the upper arm 42 as the base, the elbow joint servo motor 43 drives the forearm 44 and the palm and finger joint assembly 45 to make multi-angle adjustments, simulating the movement of the lower arm area of ​​the human hand.

[0039] For example, the elbow joint servo motor 43 drives the forearm 44 to extend outward, simulating the straight state of the human arm. Furthermore, the elbow joint servo motor 43 drives the forearm 44 to extend outward even further, achieving an outward-turning state that the human arm cannot achieve. The elbow joint servo motor 43 drives the forearm 44 to move inward, simulating the bent and retracted state of the human arm. The range of motion is greater and more flexible than that of the human arm.

[0040] The forearm 44 is provided with a palmar finger joint assembly 45 at its outer end. The forearm 44 and the palmar finger joint assembly 45 are connected by a wrist servo motor 1 5 and a wrist servo motor 2 6. The rotation directions of the wrist servo motor 1 5 and the wrist servo motor 2 6 are designed to be opposite. That is, with the forearm 44 as the base plane, the wrist servo motor 1 5 drives the palmar finger joint assembly 45 to adjust the angle forward / backward, and the wrist servo motor 2 6 drives the palmar finger joint assembly 45 to adjust the angle left / right.

[0041] By using wrist servo motor 1 5 and wrist servo motor 2 6 to drive the hand and finger joint assembly 45 to adjust forward / backward / left / right, it can not only simulate the normal multi-directional movement of the hand and wrist, but also exceed the normal range of angles that the hand and wrist cannot reach.

[0042] For example, the palm and wrist can only be adjusted forward / backward / left / right at a certain angle, which is usually an acute angle of less than 60°. However, after the wrist servo motor 15 and wrist servo motor 26 move, the palm and finger joint assembly 45 can be adjusted forward / backward / left / right at an obtuse angle of 180°. The adjustment range is larger and the flexibility is higher, making it suitable for grasping and transporting products under different spatial conditions.

[0043] Specifically, the joints of the palm and finger joint assembly 45 are all equipped with miniature servo motors 7. The miniature servo motors 7 drive the finger joints on the palm and finger joint assembly 45 to adjust their angles, so as to meet the needs of flexible adjustment of the height of multiple fingers of the palm and finger joint assembly 45. It can not only directly grasp small products, such as sheet products, but also grasp block products. It can also form a clenched shape to prevent small products from falling out, such as ball products, and soft products such as rubber and silicone. It has a wide range of applications.

[0044] At the same time, by changing the angle of one or more finger joints of the palm-finger joint assembly 45 one by one, different forms such as single-finger / full-finger grasping, pinching, and gripping can be formed to meet the grasping and transportation needs of other irregular products, provided that the volume and weight of the irregular product are within the load capacity of the palm-finger joint assembly 45.

[0045] A sensor data glove 46 is fitted over the outside of the palm and finger joint assembly 45. The sensor data glove 46 can not only provide protective wrapping for the palm and finger joint assembly 45 and its components, but also serve to prevent damage to the gripped products. Furthermore, it facilitates concealed wiring operations within the sensor data glove 46.

[0046] The forearm 44 is equipped with a bending sensor module 8 and a posture sensor module 9, which are respectively embedded in the forearm 44. The bending sensor module 8 and the posture sensor module 9 are monitored by the sensor data glove 46 to sense and monitor the hand and finger joint assembly 45, and achieve corresponding linkage effect according to the human hand gesture.

[0047] For low-requirement product gripping operations: the bending sensor module 8 and the posture sensor module 9 are collected by the Arduino system and transmitted to the computer simulation program via serial port / Wi-Fi. According to the simulation program written on the computer, the sensor data glove 46 can be used to easily set the bending degree of the finger joints of the palm finger joint assembly 45 and the pitch, deflection and rotation angles of the palm.

[0048] For high-requirement product gripping operations: the bending sensor module 8 and the attitude sensor module 9 directly interface with the IsaacSim and MuJoCo simulation engines, without the need to write code independently. Based on the code program written by the simulation engine, the glove 46 uses sensor data to set the bending degree of the finger joints of the hand finger joint assembly 45 and the pitch, deflection and rotation angles of the hand. The above two methods are only examples for illustration. This is an existing mature system software and will not be elaborated here.

[0049] Specifically, it also includes a miniature infrared sensor 10 embedded in the palm of the hand and finger joint assembly 45. After the hand and finger joint assembly 45 grasps the product, the product blocks the infrared light emitted by the miniature infrared sensor 10 located in the palm and monitors the grasping status of the product. If the product falls out of the hand and finger joint assembly 45 during the grasping action, the infrared light emitted by the miniature infrared sensor 10 will be unblocked, indicating that the product is unstable or has fallen, and an alarm can be sent to the base station.

[0050] Furthermore, a miniature pressure sensor 11 is embedded on the inner side of the finger joints of the palm and finger joint assembly 45. Through the miniature pressure sensors 11 distributed in an array on the inner side of each finger joint of the palm and finger joint assembly 45, the gripping pressure generated by each finger joint on the product is monitored in real time.

[0051] The sensor data glove 46 also adopts a high-elasticity, tear-resistant composite fabric design, while the miniature pressure sensor 11 on the inner side of the finger joint assembly 45 monitors the pressure on the product in real time through finger pressure sensing via the thin sensor data glove 46.

[0052] That is, the greater the pressure value of the miniature pressure sensor 11 at the knuckle that is in direct contact with the product, the less pressure value of the miniature pressure sensor 11 at the knuckle that is in indirect contact, and the pressure value of the miniature pressure sensor 11 at the knuckle that is not in contact is zero. If the pressure value of all the miniature pressure sensors 11 at the knuckle that are in direct / indirect contact is zero, it means that the product has been dropped and an alarm is immediately sent to the base station, forming a double safety redundancy with the miniature infrared sensor 10.

[0053] The sensor data glove 46 has a circular opening on the side near the miniature infrared sensor 10. The diameter of the circular opening is larger than the diameter of the lens of the miniature infrared sensor 10. The circular opening with a larger diameter than the lens of the miniature infrared sensor 10 avoids blocking the infrared light emitted by the miniature infrared sensor 10, thus preventing misjudgment and facilitating the normal emission of infrared light by the miniature infrared sensor 10.

[0054] In use, the rotary motor 31 controls the rotary table 32 to rotate horizontally, the upper arm motor 34 controls the mechanical upper arm 33, the lower arm motor 36 controls the mechanical lower arm 35, and the end motor 38 drives the steering motor 37 and its bionic components to adjust the vertical angle. The steering motor 37 controls the upper arm 42, forearm 44 and palm finger joint assembly 45 to rotate horizontally until the palm finger joint assembly 45 reaches the gripping point of the product.

[0055] The shoulder servo motor 41 controls the upper arm 42, forearm 44 and palm finger joint assembly 45 to move inward and outward. The elbow joint servo motor 43 drives the forearm 44 and palm finger joint assembly 45 to straighten and bend. The wrist servo motor 1 5 and wrist servo motor 2 6 drive the palm finger joint assembly 45 to adjust forward / backward / left / right at large angles. Several micro servo motors 7 distributed in an array control the activity angle of each finger joint of the palm finger joint assembly 45 until the palm finger joint assembly 45 forms different shape changes such as single finger / full finger grasping, pinching, and gripping through the sensor data glove 46, so as to grasp and transport small, irregular, soft, and irregularly shaped products.

[0056] Depending on the site conditions, the bending sensor module 8 and the posture sensor module 9 can be used to measure the bending degree of the finger joints of the palm-finger joint assembly 45, as well as the pitch, deflection, and rotation parameters of the palm. Using existing mature simulation systems, the finger angle and palm posture data can be directly output without obstruction and with high precision. This is suitable for simulating the fine operation of multiple fingers of a dexterous hand. Furthermore, the miniature infrared sensor 10 and the miniature pressure sensor 11 provide double safety redundancy for the product grasped by the palm-finger joint assembly 45 throughout the entire process.

[0057] Example 2, refer to Figures 1-7 This is the second embodiment of the present invention, which is based on the first embodiment.

[0058] The avoidance component set on the base 1 provides visual monitoring conditions for the avoidance actions of the robotic arm 3 and the bionic component through the 3D depth camera 122. It has an active avoidance safety function, forming a simulated state of human crouching and curling up, replacing the fence-like passive protection operation of traditional industrial robotic arms, and providing active avoidance safety measures for personnel and vehicles that accidentally enter the action space.

[0059] Specifically, it also includes an angle motor 121 embedded on the outside of the rotary table 32, and the output shaft of the angle motor 121 is fixed to the 3D depth camera 122. Through the angle motor 121, the visual monitoring angle and orientation of the 3D depth camera 122 are adaptively adjusted to maximize the monitoring needs of the hand and finger joint assembly 45 for the product grasping and transportation status, and reduce the blind spot range of the 3D depth camera 122.

[0060] The 3D depth camera 122 mainly collects RGB-D point cloud data of the hand and finger joint assembly 45 working scene. The monitoring content is as follows: using the scene's 3D point cloud as the modeling basis, it segments the bounding box of obstacles, outputs the 3D coordinates, shape and size of obstacles, and motion velocity vectors, and identifies dynamic objects such as personnel, foreign workpieces, and scattered materials.

[0061] The base 1 is fixed with 3D LiDAR 123 on all four sides by uprights. The 3D LiDAR 123 distributed around the base 1 monitors the overall operating space of the robotic arm 3 and the hand and finger joint assembly 45. The monitoring content is: based on the three-dimensional distance point cloud of the scene as the modeling basis, it is not affected by the lighting conditions, outputs the distance and angle of obstacles, outputs the bounding box of the obstacle space, and complements the data of the 3D depth camera 122. When the 3D depth camera 122 is affected by the lighting, it relies on the 3D LiDAR 123 to maintain environmental perception. For obstacles moving at high speed at a distance, the radar ranging response is faster, which meets the dual monitoring needs of different environments, scenes and working conditions, and is more comprehensive and accurate.

[0062] The four corner-distributed 3D LiDAR 123 and the adjustable-view 3D depth camera 122 together form a large-scale global environmental perception layer, which is responsible for monitoring the entire accessible workspace of the robotic arm 3 and the hand and finger joint assembly 45, and obtaining the position and movement trend of obstacles.

[0063] Specifically, capacitive proximity sensors 124 are fixed on the outer sides of both the robotic upper arm 33 and the robotic lower arm 35, and joint torque sensors 125 are provided on the inner sides of the upper arm motor 34, the lower arm motor 36 and the end motor 38. By using the array of distributed capacitive proximity sensors 124 and joint torque sensors 125, obstacles within the close range can be perceived, compensating for the blind spots of the 3D depth camera 122 and the 3D LiDAR 123.

[0064] When personnel, vehicles, or obstacles accidentally enter the working space of the robotic arm 3 and the hand-finger joint assembly 45, and are outside the line of sight of the camera and radar, or close to the side area of ​​the robotic arm 3 and the hand-finger joint assembly 45, they cannot be monitored by the global sensors formed by the 3D depth camera 122 and the 3D LiDAR 123. However, the array distributed capacitive proximity sensor 124 can directly read the real-time distance from the obstacle to the arm surface. Based on the relative distance signals between each sensor measuring point and the obstacle, it marks "which link has a dangerous object nearby". The joint torque sensor 125 controls the torque of the boom motor 34, the forearm motor 36 / steering motor 37 to complete active avoidance under low torque.

[0065] The forearm 44 is embedded with a six-dimensional wrist force sensor 126. This sensor collects the X / Y / Z axial forces and three-axis torques of the distal end capacities of the robotic arm 3 (palmar-finger joint assembly 45). Each servo joint calculates its output torque via motor current. The system only activates when the upper-level sensing system experiences a missed detection or blind spot failure, and the robotic arm 3 and palm-finger joint assembly 45 make physical contact with an obstacle. This immediately stops the robotic arm 3 and palm-finger joint assembly 45 and resets them to their original positions. Figure 4 The state shown simulates a human crouching and curling up, providing ample space for people, vehicles, and obstacles that accidentally wander in, serving as the last line of defense for safety.

[0066] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A bionic robotic hand based on human skeleton simulation, characterized in that: The system includes a robotic arm (3) with a base (1), which consists of a robotic upper arm (33) and a robotic forearm (35). A bionic component is provided at the end of the robotic arm (3), which simulates the human arm skeleton through the upper arm (42) and forearm (44), and an avoidance component is provided on the base (1). A 3D depth camera (122) provides visual monitoring conditions for the avoidance actions of the robotic arm (3) and the bionic component.

2. The bionic robotic hand based on human skeleton simulation as described in claim 1, characterized in that: The robotic arm (3) also includes a rotary table (32) that rotates on the base (1) via a rotary motor (31), and the rotary table (32) and the robotic arm (33) are connected by a transmission via a robotic arm motor (34).

3. The bionic robotic hand based on human skeleton simulation as described in claim 1, characterized in that: The mechanical arm (33) and the mechanical forearm (35) are driven by a forearm motor (36), and the mechanical forearm (35) and the bionic component are driven by an end motor (38). A steering motor (37) is fixed to the outside of the end motor (38) via a connector.

4. The bionic robotic hand based on human skeleton simulation as described in claim 3, characterized in that: The bionic component also includes a shoulder servo (41) fixed to the outer end of the steering motor (37), and the upper arm (42) is driven by the shoulder servo (41), and the upper arm (42) and the forearm (44) are driven by the elbow joint servo (43).

5. The bionic robotic hand based on human skeleton simulation as described in claim 1, characterized in that: The forearm (44) is provided with a palmar finger joint assembly (45) at its outer end, and the forearm (44) and the palmar finger joint assembly (45) are connected by a wrist servo motor one (5) and a wrist servo motor two (6).

6. The bionic robotic hand based on human skeleton simulation as described in claim 5, characterized in that: The joints of the palm and finger joint assembly (45) are each equipped with a miniature servo motor (7), and a sensor data glove (46) is fitted on the outside of the palm and finger joint assembly (45).

7. The bionic robotic hand based on human skeleton simulation as described in claim 1, characterized in that: The forearm (44) is respectively embedded with a bending sensor module (8) and an attitude sensor module (9), and the bending sensor module (8) and the attitude sensor module (9) use the sensing data glove (46) to sense and monitor the palm and finger joint assembly (45).

8. The bionic robotic hand based on human skeleton simulation as described in claim 5 or 6, characterized in that: The palm of the hand joint assembly (45) is embedded with a miniature infrared sensor (10), and the inner side of the finger joint of the hand joint assembly (45) is embedded with a miniature pressure sensor (11). The sensor data glove (46) has a circular opening on the side near the miniature infrared sensor (10), and the opening diameter of the circular opening is larger than the lens diameter of the miniature infrared sensor (10).

9. The bionic robotic hand based on human skeleton simulation as described in claim 2, characterized in that: The avoidance assembly also includes an angle motor (121) embedded on the outside of the rotary table (32), and the output shaft of the angle motor (121) is fixed to the 3D depth camera (122); The base (1) is fixed with 3D laser radar (123) on all four sides by uprights.

10. The bionic robotic hand based on human skeleton simulation as described in claim 2 or 3, characterized in that: Capacitive proximity sensors (124) are fixed on the outer sides of the mechanical arm (33) and the mechanical arm (35), and joint torque sensors (125) are provided on the inner sides of the arm motor (34), the arm motor (36) and the end motor (38). The forearm (44) is embedded with a wrist six-dimensional force sensor (126).

Images