CN111844047A - Dexterous hand control method and device and terminal equipment - Google Patents
Dexterous hand control method and device and terminal equipment Download PDFInfo
- Publication number
- CN111844047A CN111844047A CN202010772913.0A CN202010772913A CN111844047A CN 111844047 A CN111844047 A CN 111844047A CN 202010772913 A CN202010772913 A CN 202010772913A CN 111844047 A CN111844047 A CN 111844047A
- Authority
- CN
- China
- Prior art keywords
- learning rate
- fuzzy
- dexterous hand
- orbital
- frontal cortex
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
Abstract
The invention provides a dexterous hand control method, a device and terminal equipment, wherein the method comprises the following steps: acquiring real-time grabbing force applied to a target object by a dexterous hand, and determining a grabbing force error and a grabbing force error change rate according to the real-time grabbing force and preset expected grabbing force; carrying out fuzzy control on the grabbing force error and the grabbing force error change rate to obtain an almond body learning rate regulating quantity and an orbital and frontal cortex learning rate regulating quantity; determining a sensory input signal and a reward signal function according to the grabbing force error; and inputting the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain a dexterous hand control quantity, and controlling the dexterous hand based on the dexterous hand control quantity. The dexterous hand control method, the device and the terminal equipment provided by the invention can improve the control precision of the dexterous hand.
Description
Technical Field
The invention belongs to the technical field of dexterous hand control, and particularly relates to a dexterous hand control method, a device and terminal equipment.
Background
The dexterous hand is a novel end actuating mechanism with dexterity, universality and adaptability, can finish different grabbing and operating tasks, has the advantages of flexibility, personification, good adaptability and the like, and plays an important role in the fields of environment detection, logistics carrying, industrial assembly, rehabilitation, medical treatment, intelligent manufacturing and the like.
The dexterous hand finishes the preset task by performing grabbing operation on the target object, and needs to accurately control the dexterous hand to apply grabbing force with a proper size on the target object in the moving process so as to ensure the reliable grabbing of the dexterous hand on the target object. However, the dexterous hand control system is a nonlinear system with complexity, coupling and uncertainty, and it is difficult to establish an accurate mathematical model thereof, and although the existing dexterous hand control method based on the PID controller can realize grabbing control of the dexterous hand to a certain extent, the control precision is low, and the parameters of the PID controller are difficult to accurately adjust.
Disclosure of Invention
The invention aims to provide a dexterous hand control method, a device and terminal equipment, and aims to solve the problem of low control precision of dexterous hands in the prior art.
In a first aspect of the embodiments of the present invention, a dexterous hand control method is provided, including:
acquiring real-time grabbing force applied to a target object by a dexterous hand, and determining a grabbing force error and a grabbing force error change rate according to the real-time grabbing force and preset expected grabbing force;
carrying out fuzzy control on the grabbing force error and the grabbing force error change rate to obtain an almond body learning rate regulating quantity and an orbital and frontal cortex learning rate regulating quantity;
determining a sensory input signal and a reward signal function according to the grabbing force error;
and inputting the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain a dexterous hand control quantity, and controlling the dexterous hand based on the dexterous hand control quantity.
In a second aspect of the embodiments of the present invention, there is provided a dexterous hand control device, including:
the error calculation module is used for acquiring real-time grabbing force applied to the target object by the dexterous hand and determining grabbing force error and grabbing force error change rate according to the real-time grabbing force and preset expected grabbing force;
the fuzzy control module is used for carrying out fuzzy control on the grabbing force error and the grabbing force error change rate to obtain an almond body learning rate regulating quantity and an orbital-frontal cortex learning rate regulating quantity;
the input determining module is used for determining a sensory input signal and a reward signal function according to the grabbing force error;
and the emotion learning module is used for inputting the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain a dexterous hand control quantity, and controlling the dexterous hand based on the dexterous hand control quantity.
In a third aspect of the embodiments of the present invention, there is provided a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the dexterous hand control method when executing the computer program.
In a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the dexterous hand control method described above.
The dexterous hand control method, the device and the terminal equipment provided by the embodiment of the invention have the beneficial effects that:
compared with the traditional PID control method, the brain emotion learning model has a simple form of traditional PID control, and can automatically adjust the weight coefficient according to the signal error in the control process to realize parameter adaptive control, so that the brain emotion learning model has good adaptive capacity to a nonlinear system. Therefore, the embodiment of the invention controls the dexterous hand through the brain emotion learning model, and effectively improves the control precision compared with the prior art. On the basis, the embodiment of the invention also determines the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity based on fuzzy control, so that the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity participate in the calculation of the control quantity of the dexterous hand, and the control precision of the dexterous hand is further improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of a dexterous hand control method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a smart hand control apparatus according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of a terminal device according to an embodiment of the present invention;
fig. 4 is a block diagram of a smart hand control according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 and 4, fig. 1 is a flowchart illustrating a smart hand control method according to an embodiment of the present invention, and fig. 4 is a block diagram illustrating a smart hand control method according to an embodiment of the present invention (in fig. 4, a sense input SI represents a sense input signal, a reward signal REW represents a reward signal function, and a BEL model represents a brain emotion learning model), where the method includes:
s101: the real-time grabbing force applied to the target object by the dexterous hand is obtained, and the grabbing force error change rate are determined according to the real-time grabbing force and the preset expected grabbing force.
In this embodiment, the gripping force error is the difference between the real-time gripping force and the desired gripping force, and the rate of change of the gripping force error is the rate of change of the gripping force error.
S102: and carrying out fuzzy control on the gripping force error and the gripping force error change rate to obtain the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity.
In this embodiment, a dual-input dual-output fuzzy controller may be designed to implement step S102, where the grabbing force error and the grabbing force error change rate are used as fuzzy input signals of the fuzzy controller, and the almond body learning rate adjustment quantity and the orbital and frontal cortex learning rate adjustment quantity are used as output signals of the fuzzy controller.
S103: the sensory input signal and reward signal functions are determined based on the grip error.
In this embodiment, the sensory input signal and the reward signal function may be defined based on the functional form of the error, and the grip error is input into the defined sensory input signal and reward signal function to obtain the output values of the corresponding sensory input signal and reward signal function.
S104: and inputting the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain a dexterous hand control quantity, and controlling the dexterous hand based on the dexterous hand control quantity.
In this embodiment, the almond body learning rate adjusting amount is used for adjusting the preset learning rate of the almond body in the brain emotion learning model, and the orbital and frontal cortex learning rate adjusting amount is used for adjusting the preset learning rate of the orbital and frontal cortex in the brain emotion learning model.
In this embodiment, the control of the dexterous hand based on the dexterous hand control amount may be detailed as: and inputting the control quantity of the dexterous hand into a driving device executing mechanism for grabbing operation of the dexterous hand, and driving the dexterous hand to execute grabbing operation. The actuating mechanism of the driving device includes, but is not limited to, a motor driver, a hydraulic servo controller, or a pneumatic controller.
Compared with the traditional PID control method, the brain emotion learning model has a simple form of traditional PID control, and can automatically adjust the weight coefficient according to the signal error in the control process to realize parameter adaptive control, so that the brain emotion learning model has good adaptive capacity to a nonlinear system. Therefore, the embodiment of the invention controls the dexterous hand through the brain emotion learning model, and effectively improves the control precision compared with the prior art. On the basis, the embodiment of the invention also determines the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity based on fuzzy control, so that the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity participate in the calculation of the control quantity of the dexterous hand, and the control precision of the dexterous hand is further improved.
Optionally, as a specific implementation manner of the dexterous hand control method provided by the embodiment of the present invention, the fuzzy control is performed on the gripping force error and the gripping force error change rate to obtain the almond body learning rate adjustment amount and the orbito-frontal cortex learning rate adjustment amount, including:
and taking the gripping force error and the variation rate of the gripping force error as fuzzy input signals.
And determining a fuzzy description variable corresponding to the fuzzy input signal and a membership degree corresponding to the fuzzy description variable based on the fuzzy input signal and a preset membership function.
And determining a first weight and a second weight corresponding to the fuzzy description variable according to the fuzzy description variable and a preset weight rule table.
And determining the almond body learning rate regulating quantity based on the first weight and the membership degree corresponding to the fuzzy description variable, and determining the orbital and frontal cortex learning rate regulating quantity based on the second weight and the membership degree corresponding to the fuzzy description variable.
In this embodiment, the grabbing force error and the grabbing force error change rate can be used as fuzzy input signals of the fuzzy controller, and the almond body learning rate regulating quantity Δ α and the orbital and frontal cortex learning rate regulating quantity Δ β can be used as output variables of the fuzzy controller to construct a dual-input and dual-output fuzzy controller.
In this embodiment, the preset membership function can be directly selected from the prior art according to the actual requirement.
In this embodiment, the preset weight rule table is given by way of example as follows:
table 1 weight rule table
The weights in table 1 include a first weight and a second weight, the first weight is a weight corresponding to the calculated almond body learning rate adjustment amount, and the second weight is a weight corresponding to the calculated orbital and frontal cortex learning rate adjustment amount. That is, when calculating the almond body learning rate adjustment amount and the orbital and frontal cortex learning rate adjustment amount, the values of a1, a2, a3, b1, b2 and b3 are different, when calculating the almond body learning rate adjustment amount, the values of a1, a2, a3, b1, b2 and b3 are corresponding first weight values, and when calculating the orbital and frontal cortex learning rate adjustment amount, the values of a1, a2, a3, b1, b2 and b3 are corresponding second weight values.
In the present embodiment, the determination method of the membership degree is exemplified:
for example, if it is assumed that when a dexterous hand performs a grabbing operation, the expected grabbing force is 2.5N, the real-time grabbing force is 0.5N, the grabbing force error is 2N, the grabbing force error change rate is 0.5N/sec, and the fuzzy description variable corresponding to the grabbing force error e calculated by the grabbing force error membership function is very large, the membership of the fuzzy description variable may be set to k1, and the membership of other fuzzy description variables is set to 0; similarly, if the fuzzy description variable corresponding to the change rate of the gripping force error calculated by the membership function of the change rate of the gripping force error is rapidly increased, the membership of the fuzzy description variable may be set to k2, and the membership of other fuzzy description variables may be set to 0.
The values of k1 and k2 may be 1, and may also be set according to actual requirements, which is not limited herein.
In this embodiment, determining the almond body learning rate adjustment amount based on the first weight and the membership degree corresponding to the fuzzy description variable may be detailed as follows: and calculating products of the first weight values corresponding to all the fuzzy description variables and the membership degrees, and taking the sum of all the products as the almond body learning rate regulating quantity. The calculation method of the adjustment amount of the learning rate of the orbital-frontal cortex is the same as the above, and is not described herein again. It is to be noted, among other things, that when calculating the fuzzy description variables from the fuzzy input signal, at least one of the fuzzy description variables is obtained.
In this embodiment, on one hand, the learning rate of the almond body and the orbital and frontal cortex is adjusted on line by designing the fuzzy controller, so that the learning process of the almond body and the orbital and frontal cortex is optimized, the self-adaptive capacity of the brain emotion learning is improved, and the purpose of optimizing the control effect is achieved; on the other hand, the simple and visual weight rule table is designed to replace the traditional complex fuzzy rule table, the operation process of fuzzy control is simplified, the controlled parameters can reach the expected values more quickly, and the dynamic response speed of the dexterous hand control system is further improved.
Optionally, as a specific implementation manner of the smart hand control method provided by the embodiment of the present invention, determining an almond body learning rate adjustment amount based on a first weight and a membership degree corresponding to a fuzzy description variable, and determining an orbital-frontal cortex learning rate adjustment amount based on a second weight and a membership degree corresponding to a fuzzy description variable includes:
and determining a first fuzzy control quantity based on a first weight and a membership degree corresponding to the fuzzy description variable, and performing fuzzy solution on the first fuzzy control quantity to obtain an almond body learning rate regulating quantity.
And determining a second fuzzy control quantity based on a second weight corresponding to the fuzzy description variable and the membership degree, and performing fuzzy solution on the second fuzzy control quantity to obtain the orbital-frontal cortex learning rate regulating quantity.
In this embodiment, the control quantity of the fuzzy output can be converted to the domain of the output variable by using a gravity center method, and the adjustment quantity of the almond body learning rate and the adjustment quantity of the orbito-frontal cortex learning rate can be obtained by resolving the fuzzy.
Optionally, as a specific implementation manner of the smart hand control method provided in the embodiment of the present invention, the smart hand control method further includes a process of establishing a preset weight rule table. The establishment process of the weight rule table is as follows:
a plurality of fuzzy description variables are defined.
And setting a first weight and a second weight corresponding to each fuzzy description variable.
In this implementation, the plurality of fuzzy description variables includes fast becoming larger, slow becoming larger, constant, slow becoming smaller, fast becoming smaller.
Optionally, as a specific implementation manner of the smart hand control method provided by the embodiment of the present invention, determining the sensory input signal and the reward signal function according to the grasping force error includes:
SI＝K1e+K2∫edt
wherein SI is sensory input signal, e is grasping force error, K1、K2Is a preset adjustment factor.
REW＝K3e+K4∫edt+K5u
Wherein REW is a reward signal function, K3、K4、K5And u is the control quantity of the dexterous hand corresponding to the previous control period for presetting the adjusting coefficient.
Optionally, as a specific implementation manner of the dexterous hand control method provided by the embodiment of the present invention, the predetermined brain emotion learning model includes an amygdala body and an orbital-frontal cortex.
Inputting sensory input signals, reward signal functions, almond body learning rate regulating quantity and orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain dexterous hand control quantity, wherein the method comprises the following steps:
the learning rate of the almond body is adjusted based on the almond body learning rate regulating quantity, and the learning rate of the orbital-frontal cortex is adjusted based on the orbital-frontal cortex learning rate regulating quantity.
And respectively inputting the sensory input signal and the reward signal function into the regulated almond body and the regulated orbital and frontal cortex to obtain the output of the almond body and the output of the orbital and frontal cortex.
And determining the control quantity of the dexterous hand based on the output quantity of the almond body and the output quantity of the orbital and frontal cortex.
In this embodiment, the learning rate of the almond body is adjusted based on the almond body learning rate adjustment amount, and the learning rate of the orbital-frontal cortex is adjusted based on the orbital-frontal cortex learning rate adjustment amount, which may be detailed as:
α＝α0+Δα
β＝β0+Δβ
wherein alpha is the adjusted almond body learning rate, beta is the adjusted orbital and frontal cortex learning rate, and alpha0To adjust the pre-almond body learning rate, beta0In order to adjust the pre-orbital and frontal cortex learning rate, Δ α and Δ β are the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity, respectively.
In this embodiment, the method for determining the output of the almond body comprises:
Ath＝max(SIi)
Ai＝SIi·vi,i＝1,2,…,m
wherein, SIiIs the ith sensory input signal, m is the number of sensory input signals, viIs the weight of the almond body corresponding to the ith sensory input signal, and A is the output quantity of the almond body.
Wherein v isiThe adjustment amount calculating method comprises the following steps:
ΔVi＝α·SIimax{0,REW-A}
wherein alpha is the learning rate of the adjusted almond body, and REW is the reward signal letterNumber, Δ ViIs v isiAnd adjusting the corresponding weight value.
In this embodiment, the method for determining the output of the orbitofrontal cortex includes:
Oi＝SIi·wi,i＝1,2,…,m
wherein, wiAnd the weight of the orbital-frontal cortex corresponding to the ith sensory input signal is O, and the output of the orbital-frontal cortex is O.
Wherein, wiThe adjustment amount calculating method comprises the following steps:
ΔWi＝β·SIimax{A-O-Am+1-REW}
wherein, beta is the adjusted learning rate of the orbital frontal cortex, REW is a reward signal function, and delta W is WiAnd adjusting the corresponding weight value.
In this embodiment, v may be adjusted based on the weightiAnd wiThe adjustment is similar to the adjustment of the learning rate of the almond body and the learning rate of the orbital and frontal cortex, and the details are not repeated here.
Optionally, as a specific implementation manner of the dexterous hand control method provided by the embodiment of the present invention, the determining the dexterous hand control amount based on the output amount of the almond body and the output amount of the orbital-frontal cortex includes:
and calculating the difference value of the output quantity of the almond body and the output quantity of the orbital and frontal cortex, and taking the difference value as the control quantity of the dexterous hand.
Fig. 2 is a block diagram of a smart hand control apparatus according to an embodiment of the present invention, which corresponds to the smart hand control method of the above embodiment. For convenience of explanation, only portions related to the embodiments of the present invention are shown. Referring to fig. 2, the dexterous hand control device 20 comprises: an error calculation module 21, a fuzzy control module 22, an input determination module 23 and an emotion learning module 24.
The error calculation module 21 is configured to obtain a real-time grasping force applied to the target object by the dexterous hand, and determine a grasping force error and a grasping force error change rate according to the real-time grasping force and a preset expected grasping force.
And the fuzzy control module 22 is used for carrying out fuzzy control on the grabbing force error and the grabbing force error change rate to obtain the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity.
And the input determining module 23 is used for determining the sensory input signal and the reward signal function according to the grabbing force error.
And the emotion learning module 24 is used for inputting the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain a dexterous hand control quantity, and controlling the dexterous hand based on the dexterous hand control quantity.
Optionally, as a specific implementation manner of the smart hand control device provided in the embodiment of the present invention, the fuzzy control is performed on the gripping force error and the gripping force error change rate to obtain the almond body learning rate adjustment amount and the orbital and frontal cortex learning rate adjustment amount, including:
and taking the gripping force error and the variation rate of the gripping force error as fuzzy input signals.
And determining a fuzzy description variable corresponding to the fuzzy input signal and a membership degree corresponding to the fuzzy description variable based on the fuzzy input signal and a preset membership function.
And determining a first weight and a second weight corresponding to the fuzzy description variable according to the fuzzy description variable and a preset weight rule table.
And determining the almond body learning rate regulating quantity based on the first weight and the membership degree corresponding to the fuzzy description variable, and determining the orbital and frontal cortex learning rate regulating quantity based on the second weight and the membership degree corresponding to the fuzzy description variable.
Optionally, as a specific implementation manner of the smart manual control device provided by the embodiment of the present invention, the determining an almond body learning rate adjustment amount based on a first weight and a membership degree corresponding to a fuzzy description variable, and the determining an orbital and frontal cortex learning rate adjustment amount based on a second weight and a membership degree corresponding to a fuzzy description variable includes:
and determining a first fuzzy control quantity based on a first weight and a membership degree corresponding to the fuzzy description variable, and performing fuzzy solution on the first fuzzy control quantity to obtain an almond body learning rate regulating quantity.
And determining a second fuzzy control quantity based on a second weight corresponding to the fuzzy description variable and the membership degree, and performing fuzzy solution on the second fuzzy control quantity to obtain the orbital-frontal cortex learning rate regulating quantity.
Optionally, as a specific implementation manner of the smart phone control apparatus provided by the embodiment of the present invention, the fuzzy control module 22 is further configured to perform a step of establishing a preset weight rule table. The establishing steps of the weight rule table are as follows:
a plurality of fuzzy description variables are defined.
And setting a first weight and a second weight corresponding to each fuzzy description variable.
Optionally, as a specific implementation of the smart hand control apparatus provided as an embodiment of the present invention, determining the sensory input signal and the reward signal function according to the grasping force error includes:
SI＝K1e+K2∫edt
wherein SI is sensory input signal, e is grasping force error, K1、K2Is a preset adjustment factor.
REW＝K3e+K4∫edt+K5u
Wherein REW is a reward signal function, K3、K4、K5And u is the control quantity of the dexterous hand corresponding to the previous control period for presetting the adjusting coefficient.
Optionally, as a specific implementation of the smart hand control apparatus provided by the embodiment of the present invention, the predetermined brain emotion learning model includes an amygdala body and an orbital-frontal cortex.
Inputting sensory input signals, reward signal functions, almond body learning rate regulating quantity and orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain dexterous hand control quantity, wherein the method comprises the following steps:
the learning rate of the almond body is adjusted based on the almond body learning rate regulating quantity, and the learning rate of the orbital-frontal cortex is adjusted based on the orbital-frontal cortex learning rate regulating quantity.
And respectively inputting the sensory input signal and the reward signal function into the regulated almond body and the regulated orbital and frontal cortex to obtain the output of the almond body and the output of the orbital and frontal cortex.
And determining the control quantity of the dexterous hand based on the output quantity of the almond body and the output quantity of the orbital and frontal cortex.
Optionally, as a specific implementation of the dexterous hand control apparatus provided by the embodiment of the present invention, the determining the dexterous hand control amount based on the output amount of the almond body and the output amount of the orbital and frontal cortex includes:
and calculating the difference value of the output quantity of the almond body and the output quantity of the orbital and frontal cortex, and taking the difference value as the control quantity of the dexterous hand.
Referring to fig. 3, fig. 3 is a schematic block diagram of a terminal device according to an embodiment of the present invention. The terminal 300 in the present embodiment as shown in fig. 3 may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processor 301, the input device 302, the output device 303 and the memory 304 are all in communication with each other via a communication bus 305. The memory 304 is used to store a computer program comprising program instructions. Processor 301 is operative to execute program instructions stored in memory 304. Wherein the processor 301 is configured to call program instructions to perform the following functions for operating the modules/units in the above-described device embodiments, such as the functions of the modules 21 to 24 shown in fig. 2.
It should be understood that, in the embodiment of the present invention, the Processor 301 may be a Central Processing Unit (CPU), and the Processor may also be other general processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 302 may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of the fingerprint), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.
The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.
In specific implementation, the processor 301, the input device 302, and the output device 303 described in this embodiment of the present invention may execute the implementation manners described in the first embodiment and the second embodiment of the dexterous hand control method provided in this embodiment of the present invention, and may also execute the implementation manners of the terminal described in this embodiment of the present invention, which is not described herein again.
In another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, where the computer program includes program instructions, and the program instructions, when executed by a processor, implement all or part of the processes in the method of the above embodiments, and may also be implemented by a computer program instructing associated hardware, and the computer program may be stored in a computer-readable storage medium, and the computer program, when executed by a processor, may implement the steps of the above methods embodiments. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may include any suitable increase or decrease as required by legislation and patent practice in the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The computer readable storage medium may be an internal storage unit of the terminal of any of the foregoing embodiments, for example, a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk provided on the terminal, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the terminal. The computer-readable storage medium is used for storing a computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the terminal and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed terminal and method can be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces or units, and may also be an electrical, mechanical or other form of connection.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A dexterous hand control method, comprising:
acquiring real-time grabbing force applied to a target object by a dexterous hand, and determining a grabbing force error and a grabbing force error change rate according to the real-time grabbing force and preset expected grabbing force;
carrying out fuzzy control on the grabbing force error and the grabbing force error change rate to obtain an almond body learning rate regulating quantity and an orbital and frontal cortex learning rate regulating quantity;
determining a sensory input signal and a reward signal function according to the grabbing force error;
and inputting the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain a dexterous hand control quantity, and controlling the dexterous hand based on the dexterous hand control quantity.
2. The dexterous hand control method of claim 1, wherein said fuzzy controlling said gripping force error and said gripping force error rate of change to obtain an almond body learning rate adjustment and an orbital-frontal cortex learning rate adjustment comprises:
taking the gripping force error and the rate of change of the gripping force error as fuzzy input signals;
determining a fuzzy description variable corresponding to the fuzzy input signal and a membership degree corresponding to the fuzzy description variable based on the fuzzy input signal and a preset membership function;
determining a first weight and a second weight corresponding to the fuzzy description variable according to the fuzzy description variable and a preset weight rule table;
and determining the almond body learning rate regulating quantity based on the first weight and the membership degree corresponding to the fuzzy description variable, and determining the orbital and frontal cortex learning rate regulating quantity based on the second weight and the membership degree corresponding to the fuzzy description variable.
3. The dexterous hand control method of claim 2, wherein determining the almond body learning rate adjustment based on a first weight and a membership corresponding to the fuzzy description variable, and determining the orbital and frontal cortex learning rate adjustment based on a second weight and a membership corresponding to the fuzzy description variable comprises:
determining a first fuzzy control quantity based on a first weight and a membership degree corresponding to a fuzzy description variable, and performing fuzzy solution on the first fuzzy control quantity to obtain an almond body learning rate regulating quantity;
and determining a second fuzzy control quantity based on a second weight and the membership degree corresponding to the fuzzy description variable, and performing fuzzy solution on the second fuzzy control quantity to obtain the orbital-frontal cortex learning rate regulating quantity.
4. The dexterous hand control method of claim 2, further comprising a setup procedure of a preset weight rule table; the establishment process of the weight rule table is as follows:
defining a plurality of fuzzy description variables;
and setting a first weight and a second weight corresponding to each fuzzy description variable.
5. A dexterous hand control method as claimed in claim 1, wherein said determining a sensory input signal and a reward signal function based on said grip error comprises:
SI＝K1e+K2∫edt
wherein SI is sensory input signal, e is grasping force error, K1、K2Setting a preset adjusting coefficient;
REW＝K3e+K4∫edt+K5u
wherein REW is a reward signal function, K3、K4、K5And u is the control quantity of the dexterous hand corresponding to the previous control period for presetting the adjusting coefficient.
6. The dexterous hand control method according to claim 1, wherein the preset brain emotion learning model comprises an almond body and an orbital-frontal cortex;
the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity are input into a preset brain emotion learning model to obtain a dexterous hand control quantity, and the method comprises the following steps of:
adjusting the learning rate of the almond body based on the almond body learning rate regulating quantity, and adjusting the learning rate of the orbital-frontal cortex based on the orbital-frontal cortex learning rate regulating quantity;
inputting the sensory input signal and the reward signal function into the regulated almond body and the regulated orbital and frontal cortex respectively to obtain the output quantity of the almond body and the output quantity of the orbital and frontal cortex;
determining a dexterous hand control amount based on the almond body output amount and the orbital-frontal cortex output amount.
7. The dexterous hand control method of claim 6, wherein said determining a dexterous hand control quantity based on said almond body output quantity and said orbital-frontal cortex output quantity comprises:
and calculating the difference value of the output quantity of the almond body and the output quantity of the orbital and frontal cortex, and taking the difference value as the control quantity of the dexterous hand.
8. A dexterous hand control device, comprising:
the error calculation module is used for acquiring real-time grabbing force applied to the target object by the dexterous hand and determining grabbing force error and grabbing force error change rate according to the real-time grabbing force and preset expected grabbing force;
the fuzzy control module is used for carrying out fuzzy control on the grabbing force error and the grabbing force error change rate to obtain an almond body learning rate regulating quantity and an orbital-frontal cortex learning rate regulating quantity;
the input determining module is used for determining a sensory input signal and a reward signal function according to the grabbing force error;
and the emotion learning module is used for inputting the sensory input signal, the reward signal function, the almond body learning rate regulating quantity and the orbital and frontal cortex learning rate regulating quantity into a preset brain emotion learning model to obtain a dexterous hand control quantity, and controlling the dexterous hand based on the dexterous hand control quantity.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010772913.0A CN111844047B (en) | 2020-08-04 | 2020-08-04 | Dexterous hand control method and device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010772913.0A CN111844047B (en) | 2020-08-04 | 2020-08-04 | Dexterous hand control method and device and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111844047A true CN111844047A (en) | 2020-10-30 |
| CN111844047B CN111844047B (en) | 2021-06-11 |
Family
ID=72953480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010772913.0A Active CN111844047B (en) | 2020-08-04 | 2020-08-04 | Dexterous hand control method and device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111844047B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002049408A (en) * | 2000-06-06 | 2002-02-15 | Honda Motor Co Ltd | Fuzzy control system for controlling posture |
| CN104898421A (en) * | 2015-05-05 | 2015-09-09 | 上海大学 | Uncalibrated hand-eye coordination fussy control method based on support vector regression (SVR) learning |
| CN107450321A (en) * | 2017-08-30 | 2017-12-08 | 北京石油化工学院 | A kind of Mechanical arm control method based on brain emotion learning |
| CN107825449A (en) * | 2017-11-30 | 2018-03-23 | 南京邮电大学 | Tendon is driving singly to refer to Dextrous Hand and its control system and control method |
| CN108958037A (en) * | 2018-08-15 | 2018-12-07 | 厦门理工学院 | WAVELET FUZZY brain emotion learning control method, device, equipment and storage medium |
| CN109875659A (en) * | 2019-02-28 | 2019-06-14 | 北京航空航天大学 | Flexible needle plane based on brain emotion learning intelligent control algorithm punctures control device and method |
-
2020
- 2020-08-04 CN CN202010772913.0A patent/CN111844047B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002049408A (en) * | 2000-06-06 | 2002-02-15 | Honda Motor Co Ltd | Fuzzy control system for controlling posture |
| CN104898421A (en) * | 2015-05-05 | 2015-09-09 | 上海大学 | Uncalibrated hand-eye coordination fussy control method based on support vector regression (SVR) learning |
| CN107450321A (en) * | 2017-08-30 | 2017-12-08 | 北京石油化工学院 | A kind of Mechanical arm control method based on brain emotion learning |
| CN107825449A (en) * | 2017-11-30 | 2018-03-23 | 南京邮电大学 | Tendon is driving singly to refer to Dextrous Hand and its control system and control method |
| CN108958037A (en) * | 2018-08-15 | 2018-12-07 | 厦门理工学院 | WAVELET FUZZY brain emotion learning control method, device, equipment and storage medium |
| CN109875659A (en) * | 2019-02-28 | 2019-06-14 | 北京航空航天大学 | Flexible needle plane based on brain emotion learning intelligent control algorithm punctures control device and method |
Non-Patent Citations (1)
| Title |
|---|
| 赵国新 等: "大脑情感学习控制器的两关节机器人运动控制", 《机械设计与制造》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111844047B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Colgate | Robust impedance shaping telemanipulation | |
| CN108284442B (en) | Mechanical arm flexible joint control method based on fuzzy neural network | |
| Zeng et al. | Learning compliant robotic movements based on biomimetic motor adaptation | |
| CN107450321A (en) | A kind of Mechanical arm control method based on brain emotion learning | |
| Merel et al. | Encoder-decoder optimization for brain-computer interfaces | |
| CN111844047B (en) | Dexterous hand control method and device and terminal equipment | |
| Sharkawy et al. | A recurrent neural network for variable admittance control in human–robot cooperation: simultaneously and online adjustment of the virtual damping and Inertia parameters | |
| CN104769846A (en) | Conversion device, peripheral device and programmable controller | |
| CN111930010A (en) | LSTM network-based general MFA controller design method | |
| Dimeas et al. | Admittance neuro-control of a lifting device to reduce human effort | |
| Zhu et al. | Control of machine tools using the fuzzy control technique | |
| CN108153151A (en) | Methods of self-tuning of the MIMO full format Non-Model Controller based on systematic error | |
| CN104680418A (en) | Method and system for controlling investment position risks | |
| CN111805545B (en) | Dexterous hand control method and device and terminal equipment | |
| CN111844049B (en) | Dexterous hand grabbing control method and device and terminal equipment | |
| CN115123865A (en) | Surface treatment machine tension control method and system based on fuzzy control | |
| Richert et al. | Discrete-time weight updates in neural-adaptive control | |
| CN114376811A (en) | Wheelchair, control method and device thereof, and computer-readable storage medium | |
| JPH02226304A (en) | Group control system for fuzzy controller | |
| JPH0272404A (en) | Deciding method for membership function | |
| Tervo et al. | Recursive tuning algorithm for assist controller of a trolley crane system | |
| Sezgin et al. | Design and Implementation of Adaptive Fuzzy PD Line Following Robot | |
| Conway et al. | Using adaptive networks to model and control drug delivery | |
| Cothren et al. | Online optimization of linear-time invariant dynamical systems with cost perception | |
| JPS62226304A (en) | Ambiguity controller |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |