A facial muscle neural network intelligent bionic expression robot control system

Abstract

The present invention relates to the technical field of bionic expression robots, and is a facial muscle neural network intelligent bionic expression robot control system, comprising a support body, a power module, a control module, a muscle neural network and an expression generator. In the facial muscle neural network intelligent bionic expression robot control system of the present invention, a second sensor is connected to a grid conductor, a plurality of intersections are formed between the grid conductors, a drive unit is distributed and connected to each intersection, and the ends of the network conductors are electrically connected to a first output port, the drive unit generates a driving force under the action of a control unit, the first sensor is used to sense the longitudinal force generated by the drive unit, and the second sensor is used to sense the lateral force generated by the drive unit, so that when the first output port outputs a power difference through the grid conductor to act on each drive unit, the power difference of adjacent drive units changes continuously, thereby causing the deformation zone to generate a continuous deformation amount.

Description

Technical Field

[0001] The invention relates to the technical field of bionic expression robots, in particular to a facial muscle neural network intelligent bionic expression robot control system. Background Art

[0002] With the development of science and technology, humanoid robot technology has accelerated its evolution and has become a new frontier of scientific and technological competition. Domestic humanoid robots have been developed from scratch, with endless technological achievements, expanding application scenarios, and accelerating the localization of core components, gradually moving towards a more advanced and intelligent direction. However, due to the complex internal structure of humanoid robots, multiple power sources are required to control multiple execution units separately, making it difficult to accurately determine the control quantity. In addition, the consistency of coordinated control between multiple power sources is low, resulting in low coordination of local control quantities of bionic robots, making it difficult to achieve a natural bionic morphological effect.

[0003] The micro-expression generation device and method with patent number CN 108710325 B discloses a micro-expression driving module, N magnetic control bodies and an expression controlled body, wherein N is an integer greater than 1; the micro-expression driving module is used to generate a magnetic field according to the received control instructions to control the motion trajectory of the magnetic control body; the magnetic control body is used to be embedded in the expression controlled body and drive the expression controlled body to form different micro-expressions. This solution uses a magnetic control body to replace a complex mechanical stretching device, which reduces the cost and control complexity of the micro-expression generation device to a certain extent. The volume of the magnetic control body is smaller, and more magnetic control bodies can be placed in the same volume. However, the magnetic control bodies are independently controlled from each other, and the consistency of coordinated control is poor, and the effect of bionic natural expression changes is poor;

[0004] Harbin Institute of Technology proposed a facial expression simulation device based on hydraulic bionic actuator (patent number CN 106393126 B), which includes a simulated muscle component, a flow channel control valve component, a micro pump and a logic control unit. The simulated muscle component is installed on the simulated human face, and the simulated muscle component is connected to the micro pump connection end on the micro pump through the flow channel, and the flow channel control valve component is installed on the flow channel between the simulated muscle component and the micro pump, and the flow channel control valve component and the micro pump power supply controller are connected to the logic control unit. This solution solves the problems of complex mechanical structure system, poor stability, high cost, low simulation degree, and large size, cumbersome control and poor simulation effect of pneumatic actuator to a certain extent;

[0005] Patent No. CN100581039C discloses an inflatable dielectric elastomer hemispherical actuator, which discloses that a first pre-stretched dielectric elastomer film is attached to the inner surface of a first soft film, a second pre-stretched dielectric elastomer film is attached to the inner surface of a second soft film, the inner surface of the upper end of the first pre-stretched dielectric elastomer film is attached to the inner surface of the upper end of the second pre-stretched dielectric elastomer film, and a hemispherical space is formed between the first electrode and the substrate. This solution solves the problems of complex mechanical structure, poor flexibility, and poor bionic performance of the actuator to a certain extent.

[0006] However, although the above-mentioned prior art has solved the problem of the complex internal structure of the bionic robot to a certain extent, the bionic coordination cannot be well solved, and the control amount between each driving source is difficult to be precise. At the same time, since the requirements for the local muscle deformation amount are different during the facial expression process, and the continuous deformation amount requirement must be guaranteed, it is necessary to solve the continuity of the bionic facial muscle deformation amount and improve the coordination of the local control amount of the bionic robot. Summary of the invention

[0007] The purpose of the present invention is to provide a facial muscle neural network intelligent bionic expression robot control system, aiming to solve the continuity of bionic facial muscle deformation and improve the coordination of the local control amount of the bionic robot.

[0008] In order to solve the above technical problems, a facial muscle neural network intelligent bionic expression robot control system is provided, comprising a support body, a power module, a control module, a muscle neural network and an expression generating body, wherein the power module is provided with a plurality of first output ports; the control module comprises a plurality of control units and a plurality of first sensors, and the control module is electrically connected to the power module; the muscle neural network comprises interactively connected grid conductors, a plurality of driving units and a plurality of second sensors, the grid conductors are connected with the second sensors, a plurality of intersections are formed between the grid conductors, each of the intersections is respectively connected with the driving unit, and the ends of the grid conductors are electrically connected with the first output ports, the driving unit generates a driving force under the action of the control unit, the first sensor is used to sense the longitudinal force generated by the driving unit, and the second sensor is used to sense the lateral force generated by the driving unit; the expression generating body is connected to the support body, the expression generating body comprises a plurality of deformation zones, the deformation zones are connected with a plurality of the driving units, each of the driving units generates a continuously changing driving force, so that the deformation zones generate a continuous deformation amount.

[0009] Furthermore, the first output port outputs a power difference through the grid conductor to act on each of the driving units, and the power difference between adjacent driving units changes continuously, so that each area of ​​the deformation zone generates a continuous deformation amount.

[0010] Furthermore, the grid conductor includes a plurality of horizontal conductors, a plurality of vertical conductors and intersections located at the intersections of the horizontal conductors and the vertical conductors, wherein each of the second sensors is located on the horizontal conductors and the vertical conductors, respectively, and each of the drive units is located at the intersections, respectively, and the horizontal conductors and the vertical conductors are respectively connected to the first output port to obtain a continuous voltage signal, and a continuously changing voltage difference signal is formed at each adjacent intersection, so that the power difference of the adjacent drive units changes continuously.

[0011] Furthermore, the control units are arranged in an array below the driving unit, and the control units are electrically connected to the power module, and the control units are fixed to the supporting body.

[0012] Furthermore, the power module further comprises a plurality of second output ports, each of which is electrically connected to the control unit correspondingly, and the first sensor is abutted between the support body and each of the control units.

[0013] Furthermore, the muscle neural network also includes a plurality of memory alloys, each of which is respectively connected around the intersection of each of the horizontal wires and each of the vertical wires, so that each of the driving units produces elastic deformation relative to the horizontal wires and the vertical wires.

[0014] Furthermore, the driving unit is a first electromagnet, and the control unit is a second electromagnet.

[0015] Further, when the first electromagnet and the second electromagnet generate a first attraction force, the first electromagnet is close to the second electromagnet in the plane; when the first electromagnet and the second electromagnet generate a second attraction force, and the second attraction force is greater than the first attraction force, the first electromagnet is close to the second electromagnet in space.

[0016] Further, when the first electromagnet and the second electromagnet generate a first repulsive force, the first electromagnet gradually separates from the second electromagnet in the plane; when the first electromagnet and the second electromagnet generate a second repulsive force, and the second repulsive force is greater than the first repulsive force, the first electromagnet gradually separates from the second electromagnet in space.

[0017] Further, the driving unit is a first hydraulic pump, and the control unit is a second hydraulic pump; or, the driving unit is a first air pump, and the control unit is a second air pump.

[0018] Implementing the embodiments of the present invention will have the following beneficial effects:

[0019] 1. In the facial muscle neural network intelligent bionic expression robot control system of the present embodiment, since the second sensor is connected to the grid conductor, a plurality of intersections are formed between the grid conductors, each intersection is respectively connected to a driving unit, and the ends of the network conductors are electrically connected to the first output port. The driving unit generates a driving force under the action of the control unit, the first sensor is used to sense the longitudinal force generated by the driving unit, and the second sensor is used to sense the lateral force generated by the driving unit. Thus, when the first output port outputs the power difference through the grid conductor to act on each driving unit, the power difference of adjacent driving units changes continuously, thereby causing the deformation zone to generate a continuous deformation amount, thereby overcoming the problem of poor continuity and coordination of the bionic facial muscle deformation amount in the prior art;

[0020] 2. The facial muscle neural network intelligent bionic expression robot control system in this embodiment, since the grid conductor includes a plurality of horizontal wires, a plurality of vertical wires and an intersection point located at the intersection of the horizontal wires and the vertical wires, and the second sensor is distributed on the horizontal wires and the vertical wires, and each drive unit is located at the intersection point, the horizontal wires and the vertical wires are respectively connected to the first output port to obtain a continuous voltage signal, so that a continuously changing voltage difference signal is formed at each adjacent intersection point to act on the drive unit, thereby causing the power difference of the adjacent drive units to change continuously;

[0021] 3. The facial muscle neural network intelligent bionic expression robot control system in this embodiment, because the muscle neural network also includes a plurality of memory alloys, and each memory alloy is respectively connected around the intersection of each horizontal wire and each vertical wire, so that each drive unit can produce elastic deformation relative to the horizontal wire and the vertical wire, and then the drive unit can drive the deformation area to produce deformation and naturally restore deformation;

[0022] 4. In the facial muscle neural network intelligent bionic expression robot control system of the present embodiment, since the driving unit is the first electromagnet and the control unit is the second electromagnet, when the first electromagnet and the second electromagnet generate a first attraction force, the first electromagnet is close to the second electromagnet in the plane, so that the deformation zone produces a planar deformation expression; when the first electromagnet and the second electromagnet generate a second attraction force, and the second attraction force is greater than the first attraction force, the first electromagnet is close to the second electromagnet in space, so that the deformation zone produces a three-dimensional concave deformation expression; when the first electromagnet and the second electromagnet generate a first repulsive force, the first electromagnet gradually separates from the second electromagnet in the plane, so that the deformation zone produces a planar deformation expression; when the first electromagnet and the second electromagnet generate a second repulsive force, and the second repulsive force is greater than the first repulsive force, the first electromagnet gradually separates from the second electromagnet in space, so that the deformation zone produces a three-dimensional bulging deformation expression. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A front view of the muscle neural network according to an embodiment of the present invention;

[0025] Figure 2 A circuit diagram of a facial muscle neural network intelligent bionic expression robot control system according to an embodiment of the present invention;

[0026] Figure 3 A side view of the facial muscle neural network intelligent bionic expression robot control system according to an embodiment of the present invention;

[0027] Figure 4 for Figure 3 A partial enlarged view of the middle A;

[0028] Figure 5 A schematic diagram of a facial muscle neural network intelligent bionic expression robot control system according to an embodiment of the present invention;

[0029] Figure 6 It is a schematic diagram of the structure of the expression generator described in an embodiment of the present invention.

[0030] Among them: 100, robot control system; 110, support body; 120, power module; 121, first output port; 122, second output port; 130, control module; 131, control unit; 132, first sensor; 140, muscle neural network; 141, grid conductor; 1411, horizontal wire; 1412, vertical wire; 142, drive unit; 143, second sensor; 144, memory alloy; 150, expression generating body; 151, deformation zone. DETAILED DESCRIPTION

[0031] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The preferred embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive.

[0032] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0034] Please refer to Figure 1-Figure 6The embodiment of the present invention provides a facial muscle neural network 140 intelligent bionic expression robot control system 100, comprising a support body 110, a power module 120, a control module 130, a muscle neural network 140 and an expression generating body 150, wherein the power module 120 is provided with a plurality of first output ports 121; the control module 130 comprises a plurality of control units 131 and a plurality of first sensors 132, and the control module 130 is electrically connected to the power module 120; the muscle neural network 140 comprises an interactively connected grid conductor 141, a plurality of driving units 142 and a plurality of second sensors 143, the grid conductor 141 is connected with the second sensor 143, and the grid conductor 1 41, multiple intersections are formed between each intersection, each intersection is connected to a driving unit 142, and the ends of the grid conductor 141 are electrically connected to the first output port 121. The driving unit 142 generates a driving force under the action of the control unit 131. The first sensor 132 is used to sense the longitudinal force generated by the driving unit 142, and the second sensor 143 is used to sense the lateral force generated by the driving unit 142; the expression generating body 150 is connected to the supporting body 110, and the expression generating body 150 includes a plurality of deformation zones 151, and the deformation zone 151 is connected to a plurality of driving units 142, and each driving unit 142 generates a continuously changing driving force so that the deformation zone 151 generates a continuous deformation amount. In a specific application, the muscle neural network 140 may include at least two network conductors, each of which may be embedded in a refined grid, thereby refining the way the expression changes. Since the second sensor 143 is connected to the grid conductor 141, multiple intersections are formed between the grid conductors 141, each intersection is respectively connected to a drive unit 142, and the ends of the network conductors are electrically connected to the first output port 121. It can be understood that the grid conductor 141 is similar to a grid formed by interweaving wires, and each small grid has four intersections, each intersection radiates to the end, and is connected to the first output port 121 at the end, and the drive unit 142 is connected to the intersection to receive the signal of the first output port 121, so that the drive unit 142 generates a changing driving force under the action of the control unit 131, wherein the first sensor The sensor 132 is connected to the control unit 131, and the control unit 131 generates a reaction force. The first sensor 132 is used to sense the longitudinal force generated by the driving unit 142, so that the power module 120 can feedback and adjust the size of the longitudinal force of the driving unit 142; the second sensor 143 is connected to the grid conductor 141, and the second sensor 143 is used to sense the lateral force generated by the driving unit 142, so that the power module 120 can feedback and adjust the size of the longitudinal force of the driving unit 142. In particular, when the first output port 121 outputs the power difference through the grid conductor 141 to act on each driving unit 142, the power difference of adjacent driving units 142 changes continuously, so that the deformation zone 151 generates a continuous deformation amount, thereby solving the problem of poor continuity and coordination of the bionic facial muscle deformation amount.

[0035] In a possible embodiment, the grid conductor 141 includes a plurality of horizontal conductors 1411, a plurality of vertical conductors 1412, and intersections located at the intersections of the horizontal conductors 1411 and the vertical conductors 1412, wherein each second sensor 143 is located on the horizontal conductors 1411 and the vertical conductors 1412, respectively, and each drive unit 142 is located at the intersections, respectively, and the horizontal conductors 1411 and the vertical conductors 1412 are respectively connected to the first output port 121 to obtain a continuous voltage signal, and a continuously changing voltage difference signal is formed at each adjacent intersection, so that the power difference of adjacent drive units 142 changes continuously. In a specific application, since the grid conductor 141 includes a plurality of horizontal wires 1411, a plurality of vertical wires 1412 and an intersection point at the intersection of the horizontal wires 1411 and the vertical wires 1412, and the second sensor 143 is distributed on the horizontal wires 1411 and the vertical wires 1412, and each driving unit 142 is respectively located at the intersection point, the horizontal wires 1411 and the vertical wires 1412 are respectively connected to the first output port 121 to obtain a continuous voltage signal, so that a continuously changing voltage difference signal is formed at each adjacent intersection point to act on the driving unit 142, thereby causing the power difference of the adjacent driving units 142 to change continuously. In this way, there is no need to connect the wires to the driving unit 142 separately, avoiding the confusion of the internal structure connection and the problem of signal interference, and the value It should be noted that, for example, the input ends of the drive units 142 adjacent to the horizontal conductor 1411 are connected to the same, but the vertical conductors 1412 connected to the output ends are different. At this time, the signals controlling the adjacent vertical conductors 1412 are continuously changed, and the drive units 142 adjacent to the horizontal conductor 1411 will produce continuous power output values; similarly, the output ends of the drive units 142 adjacent to the vertical conductor 1412 are connected to the same, but the horizontal conductors 1411 connected to the input ends are different. At this time, the signals controlling the adjacent horizontal conductors 1411 are continuously changed, and the drive units 142 adjacent to the vertical conductor 1412 will produce continuous power output values, thereby enabling the adjacent drive units 142 to act on the deformation zone 151 to produce continuous and coordinated deformation.

[0036] In a possible implementation, the control units 131 form an array and are located below the driving unit 142 , and the control unit 131 is electrically connected to the power module 120 , and the control unit 131 is fixed to the support body 110 . In a specific application, since a plurality of control units 131 form an array and are located below the driving unit 142, and the control unit 131 is electrically connected to the power module 120, when the driving unit 142 moves a distance of one grid, the control unit 131 corresponding to the grid continues to exert force on the driving unit 142, so that the driving unit 142 has the ability to move multiple grids, so that the driving unit 142 drives the deformation zone 151 to produce a greater deformation, thereby causing the expression generating body 150 to produce an exaggerated expression change. In addition, it is worth mentioning that a feature of the plurality of control units 131 is that each control unit 131 can be controlled separately. For example, the driving unit 142 can generate a first action driving force under the action of the control unit 131 of the first grid, and the driving unit 142 can generate a second action driving force different from the first action driving force under the action of the control unit 131 of the second grid, thereby bringing different deformation force effects to the deformation zone 151, so that the expression generating body 150 can better refine the generation effect of the simulated expression.

[0037] In a possible implementation, the power module 120 further includes a plurality of second output ports 122, the second output ports 122 respectively correspond to the electrically connected control units 131, and the first sensor 132 abuts between the support body 110 and each control unit 131. In a specific application, the second output ports 122 respectively correspond to the electrically connected control units 131, and the first sensor 132 abuts between the support body 110 and each control unit 131, wherein the second output port 122 adapts and adjusts the command signal of the second output port 122 according to the command signal of the power module 120 to the first output port 121, and the first sensor 132 collects the longitudinal feedback signal generated by the control unit 131 in the power module 120, so that the power module 120 dynamically balances and adjusts the command signal of the second output port 122.

[0038] In a possible implementation, the muscle neural network 140 further includes a plurality of memory alloys 144, each memory alloy 144 being connected to the intersection of each horizontal conductor 1411 and each vertical conductor 1412, so that each drive unit 142 is elastically deformed relative to the horizontal conductor 1411 and the vertical conductor 1412. In a specific application, each memory alloy 144 is connected to the intersection of each horizontal conductor 1411 and each vertical conductor 1412, and it can be understood that there are four vertices in the grid body of the grid conductor 141, each vertex is an intersection, each intersection has four sides, and a memory alloy 144 is connected to each side, so that the drive unit 142 located at the intersection can move in any direction, so that each drive unit 142 can be elastically deformed on the memory alloy 144 relative to the horizontal conductor 1411 and the vertical conductor 1412, and then the drive unit 142 can drive the deformation zone 151 to produce deformation and natural recovery deformation.

[0039] In a possible embodiment, the driving unit 142 is a first electromagnet, and the control unit 131 is a second electromagnet; when the first electromagnet and the second electromagnet generate a first attraction force, the first electromagnet is close to the second electromagnet in the plane; when the first electromagnet and the second electromagnet generate a second attraction force, and the second attraction force is greater than the first attraction force, the first electromagnet is close to the second electromagnet in space; when the first electromagnet and the second electromagnet generate a first repulsive force, the first electromagnet gradually separates from the second electromagnet in the plane; when the first electromagnet and the second electromagnet generate a second repulsive force, and the second repulsive force is greater than the first repulsive force, the first electromagnet gradually separates from the second electromagnet in space. In a specific application, when the first electromagnet and the second electromagnet generate a first attractive force, the first electromagnet is close to the second electromagnet in a plane. It is worth noting that at this time, the first attractive force can be used as a load for the deformation of the expression generating body 150 and the lateral deformation of the memory alloy 144, thereby causing the deformation zone 151 to produce a planar deformation expression; when the first electromagnet and the second electromagnet generate a second attractive force, and the second attractive force is greater than the first attractive force, the first electromagnet is close to the second electromagnet in space. It is worth noting that at this time, the first attractive force can be used as a load for the deformation of the expression generating body 150 and the lateral and longitudinal deformation of the memory alloy 144, thereby causing the deformation zone 151 to produce a three-dimensional concave deformation expression, and then the expression generating body 150 can simulate the three-dimensional concave effect of the deformation zone 151.

[0040] When the first electromagnet and the second electromagnet generate a first repulsive force, the first electromagnet gradually separates in space relative to the second electromagnet. It is worth noting that at this time, the first repulsive force can be used as a load for the deformation of the expression generating body 150 and the lateral deformation of the memory alloy 144, thereby causing the deformation zone 151 to produce a planar deformation expression; when the first electromagnet and the second electromagnet generate a second repulsive force, and the second repulsive force is greater than the first repulsive force, the first electromagnet gradually separates in space relative to the second electromagnet. It is worth noting that at this time, the second repulsive force can be used as a load for the deformation of the expression generating body 150 and the lateral and longitudinal deformation of the memory alloy 144, thereby causing the deformation zone 151 to produce a three-dimensional bulging deformation expression, and the expression generating body 150 can simulate the three-dimensional bulging effect of the deformation zone 151.

[0041] In a possible implementation, the driving unit 142 is a first hydraulic pump, and the control unit 131 is a second hydraulic pump; or, the driving unit 142 is a first air pump, and the control unit 131 is a second air pump. In a specific application, when the driving unit 142 is a first hydraulic pump and the control unit 131 is a second hydraulic pump, the first output port 121 controls the power of the first hydraulic pump, and the first hydraulic pump generates a driving force acting on the deformation zone 151 to generate lateral deformation, and the second output port 122 controls the power of the second hydraulic pump, and the second hydraulic pump generates a driving force acting on the deformation zone 151 to generate longitudinal deformation, so that the expression generating body 150 generates expressions through hydraulic pressure as the driving force; similarly, when the driving unit 142 is a first air pump and the control unit 131 is a second air pump, the first output port 121 controls the power of the first air pump, and the first air pump generates a driving force acting on the deformation zone 151 to generate lateral deformation, and the second output port 122 controls the power of the second air pump, and the second air pump generates a driving force acting on the deformation zone 151 to generate longitudinal deformation, so that the expression generating body 150 generates expressions through air pressure as the driving force.

[0042] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several deformations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A facial muscle neural network intelligent bionic expression robot control system, characterized in that: include: Support body; A power module, wherein the power module is provided with a plurality of first output ports; A control module, the control module comprising a plurality of control units and a plurality of first sensors, and the control module is electrically connected to the power module; A muscle neural network, the muscle neural network comprising interconnected grid conductors, a plurality of drive units and a plurality of second sensors, the grid conductors being connected to the second sensors, a plurality of intersections being formed between the grid conductors, each of the intersections being respectively connected to the drive unit, and ends of the grid conductors being electrically connected to the first output port, the drive unit generating a driving force under the action of the control unit, the first sensor being used to sense the longitudinal force generated by the drive unit, and the second sensor being used to sense the lateral force generated by the drive unit; An expression generating body, the expression generating body is connected to the supporting body, the expression generating body comprises a plurality of deformation zones, a plurality of driving units are connected to the deformation zones, each of the driving units generates a continuously changing driving force so that the deformation zones generate a continuous deformation amount; The first output port outputs a power difference through the grid conductor to act on each of the driving units, and the power difference between adjacent driving units changes continuously, so that each area of ​​the deformation zone generates a continuous deformation amount; The grid conductor includes a plurality of horizontal conductors, a plurality of vertical conductors and intersections located at the intersections of the horizontal conductors and the vertical conductors, wherein each of the second sensors is located on the horizontal conductors and the vertical conductors, respectively, and each of the drive units is located at the intersections, respectively, and the horizontal conductors and the vertical conductors are respectively connected to the first output ports to obtain continuous voltage signals, and continuously changing voltage difference signals are formed at each adjacent intersection, so that the power difference of adjacent drive units changes continuously.

2. The facial muscle neural network intelligent bionic expression robot control system according to claim 1 is characterized in that: The control units are arranged in an array below the driving unit, and are electrically connected to the power module. The control units are fixed to the support body.

3. The facial muscle neural network intelligent bionic expression robot control system according to claim 2 is characterized in that: The power module further includes a plurality of second output ports, each of which is electrically connected to the control unit. The first sensor is abutted between the support body and each of the control units.

4. The facial muscle neural network intelligent bionic expression robot control system according to claim 1 is characterized in that: The muscle neural network also includes a plurality of memory alloys, each of which is respectively connected around the intersection of each of the horizontal conductors and each of the vertical conductors, so that each of the driving units can produce elastic deformation relative to the horizontal conductors and the vertical conductors.

5. The facial muscle neural network intelligent bionic expression robot control system according to claim 4 is characterized in that: The driving unit is a first electromagnet, and the control unit is a second electromagnet.

6. The facial muscle neural network intelligent bionic expression robot control system according to claim 5 is characterized in that: When the first electromagnet and the second electromagnet generate a first attraction force, the first electromagnet is close to the second electromagnet in plane; when the first electromagnet and the second electromagnet generate a second attraction force, and the second attraction force is greater than the first attraction force, the first electromagnet is close to the second electromagnet in space.

7. The facial muscle neural network intelligent bionic expression robot control system according to claim 5 is characterized in that: When the first electromagnet and the second electromagnet generate a first repulsive force, the first electromagnet gradually separates from the second electromagnet in a plane; when the first electromagnet and the second electromagnet generate a second repulsive force, and the second repulsive force is greater than the first repulsive force, the first electromagnet gradually separates from the second electromagnet in space.

8. The facial muscle neural network intelligent bionic expression robot control system according to claim 1 is characterized in that: The driving unit is a first hydraulic pump, and the control unit is a second hydraulic pump; or, the driving unit is a first air pump, and the control unit is a second air pump.

Images