MUSCLE EMULATION WITH DC MOTOR AND NEURAL NETWORKS FOR BIPED ROBOTS

2010 ◽  
Vol 20 (04) ◽  
pp. 341-353 ◽  
Author(s):  
HAYSSAM SERHAN ◽  
CHAIBAN G. NASR ◽  
PATRICK HENAFF
Keyword(s):  
Neural Network ◽  
Learning Algorithm ◽  
Biped Robot ◽  
Dc Motor ◽  
Muscle Model ◽  
Total Power ◽  
Total Power Consumption ◽  
Dc Motor Control ◽  
Network Identification ◽  
Online Learning Algorithm

This paper shows how to use a DC motor and its PID controller, to behave analogously to a muscle. A model of the muscle that has been learned by a NNARX (Neural Network Auto Regressive eXogenous) structure is used. The PID parameters are tuned by an MLP Network with a special indirect online learning algorithm. The calculation of the learning algorithm is performed based on a mathematical equation of the DC motor or with a Neural Network identification of the motor. For each of the two algorithms, the output of the muscle model is used as a reference for the DC motor control loop. The results show that we succeeded in forcing the physical system to behave in the same way as the muscle model with acceptable margin of error. An implementation in the knees of a simulated biped robot is realized. Simulation compares articular trajectories with and without the muscle emulator and shows that with muscle emulator, articular trajectories become closer to the human being ones and that total power consumption is reduced.

scholarly journals CMOS Implementation of ANNs Based on Analog Optimization of N-Dimensional Objective Functions

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7071
Author(s):  
Alejandro Medina-Santiago ◽  
Carlos Arturo Hernández-Gracidas ◽  
Luis Alberto Morales-Rosales ◽  
Ignacio Algredo-Badillo ◽  
Monica Amador García ◽  
...  
Keyword(s):  
Neural Network ◽  
Learning Algorithm ◽  
Building Blocks ◽  
Oxide Semiconductor ◽  
Digital Data ◽  
Total Power ◽  
Gradient Descent Method ◽  
Objective Functions ◽  
Ann Model ◽  
Total Power Consumption

The design of neural network architectures is carried out using methods that optimize a particular objective function, in which a point that minimizes the function is sought. In reported works, they only focused on software simulations or commercial complementary metal-oxide-semiconductor (CMOS), neither of which guarantees the quality of the solution. In this work, we designed a hardware architecture using individual neurons as building blocks based on the optimization of n-dimensional objective functions, such as obtaining the bias and synaptic weight parameters of an artificial neural network (ANN) model using the gradient descent method. The ANN-based architecture has a 5-3-1 configuration and is implemented on a 1.2 μm technology integrated circuit, with a total power consumption of 46.08 mW, using nine neurons and 36 CMOS operational amplifiers (op-amps). We show the results obtained from the application of integrated circuits for ANNs simulated in PSpice applied to the classification of digital data, demonstrating that the optimization method successfully obtains the synaptic weights and bias values generated by the learning algorithm (Steepest-Descent), for the design of the neural architecture.

Fuzzy Neural Network Compensator for Gantry Stage Synchronous Motion

2011 ◽  
Vol 145 ◽  
pp. 234-239 ◽  
Author(s):  
Chin Sheng Chen ◽  
Mu Han Lee
Keyword(s):  
Neural Network ◽  
Online Learning ◽  
Fuzzy Neural Network ◽  
Learning Algorithm ◽  
Tracking Error ◽  
Servo Systems ◽  
Synchronous Motion ◽  
Fuzzy Neural ◽  
Synchronous Error ◽  
Online Learning Algorithm

In this paper, a fuzzy neural network (FNN) compensator is proposed for the synchronous motion control of a gantry position stage. Firstly, the cascade control strategy is applied to reduce the single axis position tracking error. However, the synchronous error between dual servo systems is inevitable due to their inequality in characteristics and the environmental uncertainties. The FNN compensator and an online learning algorithm perform a fuzzy reasoning with two inputs of synchronous position and velocity errors between dual drive servo systems and generate the compensated force; the compensated force is fed back to the controller of each axis. The online learning algorithm adjusts the connected weighting of the neural network by using a supervised gradient descent methods, such that the define error function can be minimized. Finally, two kinds of position commands with high and low frequency are designed for the experiments, and the experimental results show that the proposed FNN compensator is feasible to improve the synchronous error of gantry stage.

The Design of Ship Course Intelligent Controller Based on Adaptive Neural Fuzzy Interference System

2011 ◽  
Vol 135-136 ◽  
pp. 1037-1043
Author(s):  
Guan Shan Hu ◽  
Hai Rong Xiao
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
High Performance ◽  
Learning Algorithm ◽  
Fuzzy Interference System ◽  
Interference System ◽  
Ship Steering ◽  
Neuro Fuzzy ◽  
Online Learning Algorithm ◽  
Adaptive Control Algorithm

Under the condition that the nonlinearity of ship steering model is considered and the assumption that the parameters of the model are uncertain, we proposed an adaptive control algorithm for ship course nonlinear system by incorporating the technique of neural network and fuzzy logic system. In the paper, we presented the structure and characteristics of Adaptive Neuro-Fuzzy Interference System (ANFIS), established the ship course controller, and realized an online learning algorithm to do online parameter estimation. We utilize fuzzy logic to solve the uncertainty problem of control system, neural network to optimize the controller parameters. To demonstrate the applicability of the proposed method, simulation results are presented at the end of this paper. The experiment shows that the ANFIS controller can achieve high performance control under parameter perturbation and other disturbances.

scholarly journals Quantized Weight Transfer Method Using Spike-Timing-Dependent Plasticity for Hardware Spiking Neural Network

2021 ◽  
Vol 11 (5) ◽  
pp. 2059
Author(s):  
Sungmin Hwang ◽  
Hyungjin Kim ◽  
Byung-Gook Park
Keyword(s):  
Neural Network ◽  
Learning Algorithm ◽  
Spike Timing ◽  
Spiking Neural Network ◽  
Spike Timing Dependent Plasticity ◽  
Dependent Plasticity ◽  
Transfer Method ◽  
Artificial Neural Network Ann ◽  
Online Learning Algorithm ◽  
Weight Transfer

A hardware-based spiking neural network (SNN) has attracted many researcher’s attention due to its energy-efficiency. When implementing the hardware-based SNN, offline training is most commonly used by which trained weights by a software-based artificial neural network (ANN) are transferred to synaptic devices. However, it is time-consuming to map all the synaptic weights as the scale of the neural network increases. In this paper, we propose a method for quantized weight transfer using spike-timing-dependent plasticity (STDP) for hardware-based SNN. STDP is an online learning algorithm for SNN, but we utilize it as the weight transfer method. Firstly, we train SNN using the Modified National Institute of Standards and Technology (MNIST) dataset and perform weight quantization. Next, the quantized weights are mapped to the synaptic devices using STDP, by which all the synaptic weights connected to a neuron are transferred simultaneously, reducing the number of pulse steps. The performance of the proposed method is confirmed, and it is demonstrated that there is little reduction in the accuracy at more than a certain level of quantization, but the number of pulse steps for weight transfer substantially decreased. In addition, the effect of the device variation is verified.

Research on Intrusion Detection Method Based on Neural Network

2011 ◽  
Vol 403-408 ◽  
pp. 1479-1482
Author(s):  
Chi Xu ◽  
Jin Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Intrusion Detection ◽  
Extraction Method ◽  
Detection Method ◽  
Learning Algorithm ◽  
Self Organizing Map ◽  
Feature Extraction Method ◽  
Online Learning Algorithm ◽  
Feature Pattern

This paper describes in Using Self-Organizing Map (SOM) neural networks and its auto-clustering ability to study intrusion detection. The feature pattern of each SOM unit is constructed using PCA feature extraction method and a simplified PCASOM model is proposed. An online learning algorithm is also given and its properties are analyzed. And then the simulation result was given.

Sign in / Sign up

Export Citation Format

Share Document