CN110640731A - Mechanical arm controller based on dopamine neuron bionic CPG system - Google Patents

Mechanical arm controller based on dopamine neuron bionic CPG system Download PDF

Info

Publication number
CN110640731A
CN110640731A CN201910915849.4A CN201910915849A CN110640731A CN 110640731 A CN110640731 A CN 110640731A CN 201910915849 A CN201910915849 A CN 201910915849A CN 110640731 A CN110640731 A CN 110640731A
Authority
CN
China
Prior art keywords
module
dopamine neuron
control signal
mechanical arm
bionic
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
Application number
CN201910915849.4A
Other languages
Chinese (zh)
Other versions
CN110640731B (en
Inventor
王江
匡载波
杨双鸣
邓斌
魏熙乐
李会艳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN201910915849.4A priority Critical patent/CN110640731B/en
Publication of CN110640731A publication Critical patent/CN110640731A/en
Application granted granted Critical
Publication of CN110640731B publication Critical patent/CN110640731B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00—Controls for manipulators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/08—Programme-controlled manipulators characterised by modular constructions
    • 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
    • B25J9/1602—Programme controls characterised by the control system, structure, architecture
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a manipulator controller based on a dopamine neuron bionic CPG system, wherein a dopamine neuron simulation model is built on an FPGA development board, then the dopamine neuron simulation model and another dopamine neuron simulation model form a dopamine neuron bionic CPG network module through a coupling synaptic current connection module, the upper computer is used for setting the expected movement track of the mechanical arm joint, and the upper computer is used for calculating the torque error between the actual movement track and the expected track of the mechanical arm joint, and transmits the data to an error correction feedback control signal module for processing, then transmits the data to a control signal modulation module, calculates corresponding input stimulation to the CPG network module, the CPG network module generates output control signals through the dopamine neuron simulation model module which is coupled with each other, the output control signals are output to the mechanical arm through the control signal output module and are transmitted to the upper computer through the USB interface module to be displayed.

Description

Mechanical arm controller based on dopamine neuron bionic CPG system
Technical Field
The invention relates to a biomedical engineering technology and a control scientific technology, in particular to a dopamine neuron bionic CPG system mechanical arm controller based on an FPGA.
Background
The mechanical arm is used as an important component in a robot design structure and plays an important role in the fields of industrial control, medical treatment and treatment, national defense science and technology, integrated circuit production and the like. With the rapid development of computer technology, the control research on the mechanical arm is more and more extensive. The production of automotive robotic arms in industrial manufacturing is a complex system of highly coupled non-linearities that is widely used in automotive assembly. In 2000, the da vinci surgical system developed by university of massachusetts, usa, accomplished various complicated surgical operations through command control of a robotic arm. The mechanical arm in the system has extremely high precision, and can perform accurate cutting in a very small area. As a new field, mechanical arm control research integrates multiple subjects such as control science, mechanical engineering, computers, artificial intelligence and the like.
The control research of the current mechanical arm is continuously developed towards the direction of intellectualization, and biological control based on nerve control and bionic control becomes the main direction of mechanical arm control. Biological Central Pattern Generators (CPGs) have now been demonstrated to be present in many invertebrates and vertebrates and to play a major role in animal motor control mechanisms. The control based on the principle of the biological center pattern generator is a bionic control method, improves the control level and capability by simulating some biological control models, and is very suitable for being used as an intelligent control method. The dopamine nervous system, located in the ventral tegmental area, is an essential component of the neural circuit for controlling motor and cognitive behaviors. The Dopamine (Dopamine) neuron model can well simulate the biological action potential and the electrophysiological characteristics of the nerve cell, and meanwhile, the CPG system based on the Dopamine neuron can also generate different control signals. On the basis, the complex bionic CPG system is realized on an FPGA development board, and the complex bionic CPG system plays an important role in high-efficiency bionic control of the mechanical arm.
The Field Programmable Gate Array (FPGA) technology is gradually favored in the Field of computational neuroscience for realizing a biological nervous system in recent years, and compared with other hardware realization methods, the FPGA has the advantages of parallel processing calculation, high integration level, repeatable configuration, low power consumption and the like, and has an important application value in the aspect of realizing a bionic CPG system to control a mechanical arm.
The prior art is still in the preliminary stage, and therefore the following disadvantages still exist: a mechanical arm controller based on a dopamine neuron bionic CPG system is not available; the human-computer interface is not perfect, and real-time control operation and data analysis cannot be performed on the mechanical arm, so that the bionic control on the mechanical arm is difficult.
Disclosure of Invention
In consideration of the wide prospect of bionic control in the field of mechanical arm control, the invention aims to provide a mechanical arm controller based on a dopamine neuron bionic CPG system. According to the invention, the mutual coupling of the dopamine neuron bionic CPG system under the simulation of the joint error feedback signal of the mechanical arm by the FPGA system generates the joint torque control signal, so that the control of the given track motion of the mechanical arm can be realized. Because the CPG system composed of mutually coupled dopamine neurons has stronger anti-interference performance and can be quickly recovered under the action of an external disturbance signal, the nerve control signal generated by the bionic CPG system composed of mutually coupled dopamine neurons has stronger robustness and stability. The technical scheme is as follows:
a dopamine neuron bionic CPG system-based manipulator controller is characterized in that a dopamine neuron simulation model is built on an FPGA development board, then the dopamine neuron simulation model and another dopamine neuron simulation model form a dopamine neuron bionic CPG network module through a coupling synaptic current connection module, a crystal oscillator is arranged in the FPGA development board to generate a clock signal of 50MHz, then frequency division processing is carried out on the frequency through a frequency divider in an IP soft core in Quartus II to be input into the dopamine neuron bionic CPG network module, a manipulator joint expected movement track is set through an upper computer, a torque error between the actual movement track and the expected track of the manipulator joint is calculated through the upper computer and is transmitted to an error correction feedback control signal module for processing, then the torque error is transmitted to a control signal modulation module, and corresponding input stimulation to the CPG network module is calculated, the CPG network module generates output control signals through the dopamine neuron simulation model module which is coupled with each other, the output control signals are output to the mechanical arm through the control signal output module and are transmitted to the upper computer through the USB interface module to be displayed. And controlling and modulating corresponding coupling parameters in the coupling synaptic current calculation module and a control signal frequency mode of the control signal output module according to the movement condition of the mechanical arm, so as to ensure that the mechanical arm is stably executed under the control signal under the condition of external interference. Meanwhile, the upper computer also acquires the specific track of the mechanical arm and the specific waveform of the control signal through the signal acquisition port and displays the specific track and the specific waveform on a control interface of the upper computer so as to observe whether the mechanical arm normally moves.
The error correction calculation feedback module receives an externally input mechanical arm track signal and outputs a corrected signal to the control signal modulation module for processing.
The dopamine neuron bionic CPG network module comprises a dopamine neuron module and a coupling synaptic current calculation module, the dopamine neuron simulation model is discretized in an FPGA by adopting an Euler method and is built by adopting a pipeline technology, and the coupling synaptic current calculation module calculates the corresponding synaptic current between neurons according to different coupling parameters.
The upper computer operation interface is compiled by Labview development and is connected with an upper computer through VISA, the expected track of each joint of the mechanical arm and the CPG network coupling parameter are set through the operation interface, and meanwhile, the human-computer operation interface can display the control signal and the specific track of the mechanical arm in real time.
Drawings
FIG. 1 is a schematic diagram of a controller system according to the present invention;
FIG. 2 is a dopamine neuron voltage measurement calculation module;
FIG. 3 is a coupled synaptic current calculation module;
FIG. 4 is a schematic view of a human-machine interface according to the present invention;
in the figure:
the system comprises an FPGA development board 2, an upper computer 3, a dopamine neuron calculation module 4, a coupling synaptic current calculation module 5, a clock module 6, an error correction feedback module 7, a torque error signal 8, an output control signal 9, a USB interface module 10, a man-machine operation interface 11, a control signal modulation module 12, a bionic CPG network module 13, dopamine neuron coupling parameters 14, an Ik current lookup table 15, an IsNa current lookup table 16, an Ina current lookup table 17, a Ca variable lookup table 18, a coupling connection ROM memory 19, a basic operation frame 20, a display interface 21, a coupling parameter configuration frame 22, an output control signal frequency configuration frame 23, a simulation parameter configuration frame 24, a crystal oscillator 25, a frequency divider 26 and a control signal output module.
Detailed Description
The structure of the manipulator controller based on the dopamine neuron bionic CPG system is described below with reference to the accompanying drawings.
The design idea of the manipulator controller based on the dopamine neuron bionic CPG system is that firstly a dopamine neuron simulation model is built on an FPGA development board, and then the dopamine neuron simulation model and another dopamine neuron simulation model form a dopamine neuron bionic CPG network module through a coupling synaptic current connection module. A crystal oscillator arranged in an FPGA development board generates a clock signal of 50MHz, and then frequency division processing is carried out on the frequency through a frequency divider in an IP soft core in Quartus II to be input into a dopamine neuron bionic CPG network module. The system sets the expected movement track of the mechanical arm joint through an upper computer, calculates the torque error between the actual movement track and the expected track of the mechanical arm joint through the upper computer, transmits the torque error to an error correction feedback control signal module for processing, then transmits the torque error to a control signal modulation module, calculates the corresponding input stimulation to a CPG network module, generates an output control signal through a dopamine neuron simulation model module which is mutually coupled, outputs the output control signal to the mechanical arm through a control signal output module, and transmits the output control signal to the upper computer through a USB interface module for display. And controlling and modulating corresponding coupling parameters in the coupling synaptic current calculation module and a control signal frequency mode of the control signal output module according to the movement condition of the mechanical arm, so as to ensure that the mechanical arm is stably executed under the control signal under the condition of external interference. Meanwhile, the upper computer also acquires the specific track of the mechanical arm and the specific waveform of the control signal through the signal acquisition port and displays the specific track and the specific waveform on a control interface of the upper computer so as to observe whether the mechanical arm normally moves.
The error correction calculation feedback module receives an externally input mechanical arm track signal and outputs a corrected signal to the control signal modulation module for processing.
The clock module consists of an FPGA development board built-in crystal oscillator and a frequency divider module. The frequency divider is generated by using an IP soft core in QuratusII software, a crystal oscillator is arranged in an FPGA development board to generate a 50MHz clock signal, and the frequency divider performs frequency division processing on the clock signal and inputs the signal into a dopamine neuron bionic CPG network module for calculating a neuron model.
The dopamine neuron bionic CPG network module comprises a dopamine neuron module and a coupling synaptic current calculation module. The dopamine neuron simulation model is discretized in an FPGA (field programmable gate array) by adopting an Euler method and is built by adopting a pipeline technology, a complex ordinary differential equation is calculated in parallel, a complex nonlinear function in the model is realized by piecewise linear optimization and a lookup table, and a coupled synaptic current calculation module calculates corresponding synaptic currents among neurons according to different coupling parameters.
The upper computer operation interface is compiled by Labview development, is connected with an upper computer through a VISA (visual Instrument Architecture), sets the expected track of each joint of the mechanical arm and the CPG network coupling parameter through the operation interface, and simultaneously can display the control signal and the specific track of the mechanical arm in real time.
The manipulator controller based on the dopamine neuron bionic CPG system consists of an FPGA development board and an upper computer. The FPGA development board is used for realizing an error correction feedback module, a control signal modulation module, a control signal output module and a dopamine neuron CPG network module. The upper computer is used for designing a man-machine operation interface and realizing communication with the FPGA development board through the USB interface module. The following is illustrated:
as shown in fig. 1, a hardware platform is designed, and the dopamine neuron bionic CPG network module is composed of a dopamine neuron simulation model and a coupling synaptic current calculation module. The FPGA development board is a development board produced by Altera corporation, firstly discretizing and building a neuron streamline model by adopting an Euler method according to a dopamine neuron simulation model, and performing piecewise linear optimization design on a complex nonlinear function in the model and realizing the piecewise linear optimization design by using a lookup table. The clock module for calculating the synaptic current between dopamine neurons by the coupling synaptic current calculation module generates a 50NHz original clock signal through an internal crystal oscillator of the FPGA development board, adjusts the clock signal through a frequency divider generated by an IP soft core in the Quartus II and inputs the clock signal into the dopamine neuron bionic CPG network module. The upper computer and the FPGA development board are communicated, and relevant parameters in the coupling synaptic current calculation module are set in a human-computer operation interface through a coupling parameter data bus, so that the output signal of the dopamine neuron bionic CPG network module is controlled.
As shown in fig. 2, the voltage variation data link calculation module in the dopamine neuron model mainly comprises an adder, a multiplier and a lookup table module, wherein different types of ion channels are arranged on the membrane of the dopamine neuron, the conductance of the ion channels changes with the change of activation variables and deactivation variables of the ion channels, and the mathematical formula can be described as follows:
Figure BDA0002215583530000051
Figure BDA0002215583530000052
the parameters are as follows:
film capacitance: c 1. mu.F/cm2
Ion channel counter potential: ek＝-90mV,El＝-90mV,ECa＝50mV,ENa＝55mV
Synaptic current IsynAn output value from a coupled synaptic current calculation module is received.
Other parameter values: gKCa＝7.8mS/cm2,
Figure BDA0002215583530000053
gsNa＝0.13mS/cm2,
Figure BDA0002215583530000054
Figure BDA0002215583530000055
gl＝0.18mS/cm2
FIG. 3 shows a coupled synaptic current calculation module that calculates synaptic currents of dopamine neurons according to a coupling parameter ROM memory, which can be described by the following equation:
Isyn＝g(v-Esyn)
wherein v is dopamine neuronal membrane potential, synaptic back-potential EsysG is the coupling parameter between dopamine neurons.
And (5) a man-machine operation interface.
A human-computer operation interface is designed and realized by using Labivew in the upper computer, and the FPGA development board realizes data communication work with the upper computer through a USB interface module. And when Labview programming is used, a multithreading programming technology is adopted, and the multithreading technology is adopted to display a graph curve in real time and simultaneously give consideration to the data processing function, so that continuous data acquisition is ensured. The human-computer operation interface comprises a basic operation frame used for realizing basic operation on the human-computer operation interface; the method comprises the following steps of configuring neuron coupling parameters and simulating parameter configuration options, performing parameter configuration on the dopamine neuron CPG network, performing mode selection on control signals output by the dopamine neuron CPG system, and displaying the output control signals in real time.

Claims (1)

1. A dopamine neuron bionic CPG system-based manipulator controller is characterized in that a dopamine neuron simulation model is built on an FPGA development board, then the dopamine neuron simulation model and another dopamine neuron simulation model form a dopamine neuron bionic CPG network module through a coupling synaptic current connection module, a crystal oscillator is arranged in the FPGA development board to generate a clock signal of 50MHz, then frequency division processing is carried out on the frequency through a frequency divider in an IP soft core in Quartus II to be input into the dopamine neuron bionic CPG network module, a manipulator joint expected movement track is set through an upper computer, a torque error between the actual movement track and the expected track of the manipulator joint is calculated through the upper computer and is transmitted to an error correction feedback control signal module for processing, then the torque error is transmitted to a control signal modulation module, and corresponding input stimulation to the CPG network module is calculated, the CPG network module generates an output control signal through the dopamine neuron simulation model module which is coupled with each other, outputs the output control signal to the mechanical arm through the control signal output module and transmits the output control signal to the upper computer for display through the USB interface module; controlling and modulating corresponding coupling parameters in the coupling synaptic current calculation module and a control signal frequency mode of the control signal output module according to the movement condition of the mechanical arm, so as to ensure that the mechanical arm is stably executed under the control signal under the condition of external interference; meanwhile, the upper computer also acquires the specific track of the mechanical arm and the specific waveform of the control signal through a signal acquisition port and displays the specific track and the specific waveform on a control interface of the upper computer;
the error correction calculation feedback module receives an externally input mechanical arm track signal and outputs a corrected signal to the control signal modulation module for processing;
the dopamine neuron bionic CPG network module comprises a dopamine neuron module and a coupling synaptic current calculation module, wherein the dopamine neuron simulation model is discretized in an FPGA by adopting an Euler method and is built by adopting a pipeline technology, and the coupling synaptic current calculation module calculates corresponding synaptic currents among neurons according to different coupling parameters;
the upper computer operation interface is compiled by Labview development and is connected with an upper computer through VISA, the expected track of each joint of the mechanical arm and the CPG network coupling parameter are set through the operation interface, and meanwhile, the human-computer operation interface can display the control signal and the specific track of the mechanical arm in real time.
CN201910915849.4A 2019-09-25 2019-09-25 Mechanical arm controller based on dopamine neuron bionic CPG system Active CN110640731B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910915849.4A CN110640731B (en) 2019-09-25 2019-09-25 Mechanical arm controller based on dopamine neuron bionic CPG system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910915849.4A CN110640731B (en) 2019-09-25 2019-09-25 Mechanical arm controller based on dopamine neuron bionic CPG system

Publications (2)

Publication Number Publication Date
CN110640731A true CN110640731A (en) 2020-01-03
CN110640731B CN110640731B (en) 2022-08-19

Family

ID=69011295

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910915849.4A Active CN110640731B (en) 2019-09-25 2019-09-25 Mechanical arm controller based on dopamine neuron bionic CPG system

Country Status (1)

Country Link
CN (1) CN110640731B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112757290A (en) * 2020-12-12 2021-05-07 天津大学 Mechanical arm control method based on FPGA
CN113580138A (en) * 2021-08-13 2021-11-02 郑州大学 Robot trajectory planning method based on Tau-E

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140031986A1 (en) * 2012-01-11 2014-01-30 Jonathan Spitz Robot, device and a method for central pattern generator (CPG) based control of a movement of the robot
CN104541306A (en) * 2013-08-02 2015-04-22 奥克兰单一服务有限公司 System for neurobehavioural animation
CN107169184A (en) * 2017-05-04 2017-09-15 天津大学 Substrate nuclear network beta rhythm and pace of moving things analogue systems based on FPGA
CN107351080A (en) * 2017-06-16 2017-11-17 浙江大学 A kind of hybrid intelligent research system and control method based on array of camera units
CN108372506A (en) * 2018-05-16 2018-08-07 中南大学 A kind of anthropomorphic robot based on CPG models is adaptively walked framework implementation method
CN109352644A (en) * 2018-09-14 2019-02-19 天津大学 Manipulator motion rhythm detection method based on CPG neuroid

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140031986A1 (en) * 2012-01-11 2014-01-30 Jonathan Spitz Robot, device and a method for central pattern generator (CPG) based control of a movement of the robot
CN104541306A (en) * 2013-08-02 2015-04-22 奥克兰单一服务有限公司 System for neurobehavioural animation
CN107169184A (en) * 2017-05-04 2017-09-15 天津大学 Substrate nuclear network beta rhythm and pace of moving things analogue systems based on FPGA
CN107351080A (en) * 2017-06-16 2017-11-17 浙江大学 A kind of hybrid intelligent research system and control method based on array of camera units
CN108372506A (en) * 2018-05-16 2018-08-07 中南大学 A kind of anthropomorphic robot based on CPG models is adaptively walked framework implementation method
CN109352644A (en) * 2018-09-14 2019-02-19 天津大学 Manipulator motion rhythm detection method based on CPG neuroid

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
雷静桃等: "四足机器人对角小跑步态控制策略分析", 《上海大学学报(自然科学版)》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112757290A (en) * 2020-12-12 2021-05-07 天津大学 Mechanical arm control method based on FPGA
CN113580138A (en) * 2021-08-13 2021-11-02 郑州大学 Robot trajectory planning method based on Tau-E
CN113580138B (en) * 2021-08-13 2022-07-19 郑州大学 Robot track planning method based on Tau-E

Also Published As

Publication number Publication date
CN110640731B (en) 2022-08-19

Similar Documents

Publication Publication Date Title
CN109352644B (en) Mechanical arm movement rhythm control method based on CPG (coherent population) neuron network
Kozma et al. Chaotic resonance—methods and applications for robust classification of noisy and variable patterns
CN110640731B (en) Mechanical arm controller based on dopamine neuron bionic CPG system
CN104573238B (en) A kind of circuit design method of memristor cell neural network
CN104112066B (en) Epilepsy state closed-loop control experiment platform based on FPGA
CN104375878A (en) FPGA simulation system for modulating hippocampus network rhythm through weak electromagnetic stimulation
Li et al. Development of adaptive locomotion of a caterpillar-like robot based on a sensory feedback CPG model
Zhang et al. A cerebellum-inspired prediction and correction model for motion control of a musculoskeletal robot
CN102830629B (en) Testing device and method of power electronic control system
Bevilacqua et al. Artificial neural networks for feedback control of a human elbow hydraulic prosthesis
Sun et al. Real-time human intention recognition of multi-joints based on MYO
Wang et al. Finite-time modified combination synchronization of memristive FitzHugh–Nagumo circuit with unknown disturbances
Ismeal et al. DC motor identification based on Recurrent Neural Networks
Massone et al. The role of plant properties in arm trajectory formation: A neural network study
CN210090954U (en) Neuron analog circuit
CN107590360B (en) Neuron ion channel dynamic characteristic experiment platform based on FPGA
Ji et al. Dynamical analysis of periodic bursting in piece-wise linear planar neuron model
Porras et al. Bio-inspired coupled oscillatory phase reset control system applied to movement in an underwater vehicle
Pyle et al. A model of reward-modulated motor learning with parallelcortical and basal ganglia pathways
Chen et al. High-order iterative learning control of functional neuromuscular stimulation systems
WO2024197457A1 (en) Closed-loop adaptive brain‑machine interface decoding method and device based on reinforcement learning
Liu et al. Developing Robot Reaching Skill via Look-ahead Planning
CN108319149A (en) A kind of electromagnetic switch wisdom control system with Self-learning control pattern
Sruthi et al. Spiking Neuron Model with Improved Plausibility using Artificial Bee Colony Algorithm
Marian et al. SIMULATING THE FACIAL EXPRESSIONS OF A BIOMIMETIC STRUCTURES

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