Control system for the Khepera robot by a neural network with competition and cooperation

This article describes a new approach to control systems for a mobile robot Khepera by using a neural network with competition and cooperation as the processing unit for the robot sensors. Competition makes only one neuron active, while cooperation keeps them all active. In our research, we find that the Khepera controlled by this neural network can maintain a smoother trajectory than when it is controlled by the output values of its own sensors, especially in noisy environments. This work was presented in part at the Fifth International Symposium on Artificial Life and Robotics, Oita, Japan, January 26–28, 2000     

Noise analysis of robot manipulator using neural networks

Due to a lot of robot manipulators application in industry, low noise degree is very important criteria for robot manipulator's joints. In this paper, joint noise problem of a robot manipulator with five joints is investigated both theoretically and experimentally. The investigation is consisted of two steps. First step is to analyze the noise of joints using a hardware and software. The hardware is a part of noise sensors. The second step; according to experimental results, some neural networks are employed for finding robust neural noise analyzer. Five types of neural networks are used to compare each other. From the results, it is noted that the proposed RBFNN gives the best results for analyzing joint noise of the robot manipulator.     

Fault detection on robot manipulators using artificial neural networks

Nowadays, gas welding applications on vehicle’s parts with robot manipulators have increased in automobile industry. Therefore, the speed of end-effectors of robot manipulator is affected on each joint during the welding process with complex trajectory. For that reason, it is necessary to analyze the noise and vibration of robot’s joints for predicting faults. This paper presents an experimental investigation on a robot manipulator, using neural network for analyzing the vibration condition on joints. Firstly, robot manipulator’s joints are tested with prescribed of trajectory end-effectors for the different joints speeds. Furthermore, noise and vibration of each joint are measured. And then, the related parameters are tested with neural network predictor to predict servicing period. In order to find robust and adaptive neural network structure, two types of neural predictors are employed in this investigation. The results of two approaches improved that an RBNN type can be employed to predict the vibrations on industrial robots.     

Cooperative control of multiple neural networks for an indoor blimp robot

We report on the cooperative control of multiple neural networks for an indoor blimp robot. In our research group, the indoor blimp robot has been studied to achieve various flying robot applications. The objective of this article is to propose a robust controller that can adapt to mechanical accidents such as the breakdown of propellers. In our proposed method, each propeller thrust is independently calculated by a small neural network. We confirm the advantage of the proposed method against the control by a single large neural network. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

基于神经网络的微分对策控制器设计

采用伴随－BP技术，将微分对策的两点边值求解问题转化两个神经网络的学习问题，训练后的两个神经网络分别作为对策双方的最优控制器在线使用，避免了直接求解复杂的两点边值问题，对追逃微分对策问题的仿真结果表明，该方法对初始条件和噪声具有较好的鲁棒性。     

Application of a neural network to the generation of a robot arm trajectory

We propose a neural network model generating a robot arm trajectory. The developed neural network model is based on a recurrent-type neural network (RNN) model calculating the proper arm trajectory based on data acquired by evaluation functions of human operations as the training data. A self-learning function has been added to the RNN model. The proposed method is applied to a 2-DOF robot arm, and laboratory experiments were executed to show the effectiveness of the proposed method. Through experiments, it is verified that the proposed model can reproduce the arm trajectory generated by a human. Further, the trajectory of a robot arm is successfully modified to avoid collisions with obstacles by a self-learning function.This work was presented, in part, at the 9th International Symposium on Artificial Life and Robotics, Oita, Japan, January 28–30, 2004     

Genetic algorithm design of neural network and fuzzy logic controllers

This paper discusses the design of neural network and fuzzy logic controllers using genetic algorithms, for real-time control of flows in sewerage networks. The soft controllers operate in a critical control range, with a simple set-point strategy governing “easy” cases. The genetic algorithm designs controllers and set-points by repeated application of a simulator. A comparison between neural network, fuzzy logic and benchmark controller performance is presented. Global and local control strategies are compared. Methods to reduce execution time of the genetic algorithm, including the use of a Tabu algorithm for training data selection, are also discussed. The results indicate that local control is superior to global control, and that the genetic algorithm design of soft controllers is feasible even for complex flow systems of a realistic scale. Neural network and fuzzy logic controllers have comparable performance, although neural networks can be successfully optimised more consistently.     

基于郭涛算法的演化神经网络

提出了一种新的演化神经网络算法GTEANN,该算法基于高效的郭涛算法,同时完成在网络结构空间和权值空间的搜索,以实现前馈神经网络的自动化设计。本方法采用的编码方案直观有效,基于该编码表示,神经网络的学习过程是一个复杂的混合整实数非线性规划问题,例如杂交操作包括网络的同构和规整处理。初步实验结果表明该方法收敛,能够达到根据训练样本自动优化设计多层前馈神经网络的目的。     

Genetic design of real-time neural network controllers

The use of genetic algorithms to design neural networks for real-time control of flows in sewerage networks is discussed. In many control applications, standard supervised learning techniques (such as back-propagation) cannot be used through lack of training data. Reinforcement learning techniques, such as genetic algorithms, are a computationally-expensive but viable alternative if a simulator is available for the system in question. The paper briefly describes why genetic algorithms and neural networks were selected, then reports the results of a feasibility study. This demonstrates that the approach does indeed have merits. The implications of high computational cost are discussed, in terms of scaling up to significantly complex problems.     

Real-time implementation of a dynamic fuzzy neural networks controller for a SCARA

This paper presents the design, development and implementation of a Dynamic Fuzzy Neural Networks (D-FNNs) Controller suitable for real-time industrial applications. The unique feature of the D-FNNs controller is that it has dynamic self-organising structure, fast learning speed, good generalisation and flexibility in learning. The approach of rapid prototyping is employed to implement the D-FNNs controller with a view of controlling a Selectively Compliance Assembly Robot Arm (SCARA) in real time. Simulink, an iterative software for simulating dynamic systems, is used for modelling, simulation and analysis of the dynamic system. The D-FNNs controller was implemented through Real-Time Workshop (RTW). RTW generates C-codes from the Simulink block diagrams and in turn, the generated codes (object codes) are downloaded to the dSPACE DS1102 floating-point processor, together with the supporting files, for execution. The performance of the D-FNNs controller was found to be superior and it matches favourably with the simulation results.     

Adaptive RBF neural network control of robot with actuator nonlinearities

In this paper, an adaptive neural network control scheme for robot manipulators with actuator nonlinearities is presented. The control scheme consists of an adaptive neural network controller and an actuator nonlinearities compensator. Since the actuator nonlinearities are usually included in the robot driving motor, a compensator using radial basis function (RBF) network is proposed to estimate the actuator nonlinearities and eliminate their effects. Subsequently, an adaptive neural network controller that neither requires the evaluation of inverse dynamical model nor the time-consuming training process is given. In addition, GL matrix and its product operator are introduced to help prove the stability of the closed control system. Considering the adaptive neural network controller and the RBF network compensator as the whole control scheme, the closed-loop system is proved to be uniformly ultimately bounded (UUB). The whole scheme provides a general procedure to control the robot manipulators with actuator nonlinearities. Simulation results verify the effectiveness of the designed scheme and the theoretical discussion.     

Feature extraction method for a robot map using neural networks

Many map-building algorithms using ultrasonic sensors have been developed for mobile robot applications. In indoor environments, the ultrasonic sensor system gives some uncertain data. To compensate for this effect, a new feature extraction method using neural networks is proposed. A new, effective representation of the target is defined, and the reflection wave data patterns are learnt using neural networks. As a consequence, the targets are classified as planes, corners, or edges, which all frequently occur in indoor environments. We constructed our own robot system for the experiments which were carried out to show the performance. This work was presented in part at the 7th International Symposium on Artificial Life and Robotics, Oita, Japan, January 16–18, 2002     

Improved competitive learning neural networks for network intrusion and fraud detection

In this research, we propose two new clustering algorithms, the improved competitive learning network (ICLN) and the supervised improved competitive learning network (SICLN), for fraud detection and network intrusion detection. The ICLN is an unsupervised clustering algorithm, which applies new rules to the standard competitive learning neural network (SCLN). The network neurons in the ICLN are trained to represent the center of the data by a new reward-punishment update rule. This new update rule overcomes the instability of the SCLN. The SICLN is a supervised version of the ICLN. In the SICLN, the new supervised update rule uses the data labels to guide the training process to achieve a better clustering result. The SICLN can be applied to both labeled and unlabeled data and is highly tolerant to missing or delay labels. Furthermore, the SICLN is capable to reconstruct itself, thus is completely independent from the initial number of clusters.To assess the proposed algorithms, we have performed experimental comparisons on both research data and real-world data in fraud detection and network intrusion detection. The results demonstrate that both the ICLN and the SICLN achieve high performance, and the SICLN outperforms traditional unsupervised clustering algorithms.     

Consensus-based distributed cooperative learning control for a group of discrete-time nonlinear multi-agent systems using neural networks

This paper focuses on the cooperative learning capability of radial basis function neural networks in adaptive neural controllers for a group of uncertain discrete-time nonlinear systems where system structures are identical but reference signals are different. By constructing an interconnection topology among learning laws of NN weights in order to share their learned knowledge on-line, a novel adaptive NN control scheme, called distributed cooperative learning control scheme, is proposed. It is guaranteed that if the interconnection topology is undirected and connected, all closed-loop signals are uniform ultimate bounded and tracking errors of all systems can converge to a small neighborhood around the origin. Moreover, it is proved that all estimated NN weights converge to a small neighborhood of their common optimal value along the union of all state trajectories, which means that the estimated NN weights reach consensus with a small consensus error. Thus, all learned NN models have the better generalization capability than ones obtained by the deterministic learning method. The learned knowledge is also adopted to control a class of uncertain systems with the same structure but different reference signals. Finally, a simulation example is provided to verify the effectiveness and advantages of the distributed cooperative learning control scheme developed in this paper.     

基于神经网络的机器人运动模型辨识及其实验研究

针对机器人楚模中不确定因素的影响，采用神经网络辨识机器人输入输出间的非线性关系，建立机器人的运动学模型，为了提高神经网络的辨识速度，基于Elman动态递归网络，通过增加网络输入输出的部分信息，提出一种新的动态神经网络结构——状态廷迟输入动态递归神经网络(SDIDRNN)，提高了网络的学习速度和稳态精度。以PowerCube^TM模块化机器人为研究对象，把根据机器人返回的关节位置信息和利用OPTOTRAK3020三维运动测量系统测得的机器人末端位置信患作为SDIDRNN的学习样本，对包含各种影响因素的机器人运动模型进行辨识，得到了满意的结果，说明了该神经网络的优越性。     

Stochastic neural networks

The first purpose of this paper is to present a class of algorithms for finding the global minimum of a continuous-variable function defined on a hypercube. These algorithms, based on both diffusion processes and simulated annealing, are implementable as analog integrated circuits. Such circuits can be viewed as generalizations of neural networks of the Hopfield type, and are called diffusion machines.Our second objective is to show that learning in these networks can be achieved by a set of three interconnected diffusion machines: one that learns, one to model the desired behavior, and one to compute the weight changes.This research was supported in part by U.S. Army Research Office Grant DAAL03-89-K-0128.     

Adaptive L_2 control of nonlinear systems using neural networks

An adaptive neural network controller is developed to achieve output-tracking of a class of nonlinear systems. The global L2 stability of the closed-loop system is established. The proposed control design overcomes the limitation of the conventional adaptive neural control design where the modeling error brought by neural networks is assumed to be bounded over a compact set. Moreover,the generalized matching conditions are also relaxed in the proposed L2 control design as the gains for the external disturbances entering the system are allowed to have unknown upper bounds.     

Design of a PID optimized neural networks and PD fuzzy logic controllers for a two‐wheeled mobile robot

In this paper, two intelligent techniques for a two‐wheeled differential mobile robot are designed and presented: A smart PID optimized neural networks based controller (SNNPIDC) and a PD fuzzy logic controller (PDFLC). Basically, mobile robots are required to work and navigate under exigent circumstances where the environment is hostile, full of disturbances such as holes and stones. The robot navigation leads to an autonomous decision making to overcome an obstacle and/or to stop the engine to protect it. In fact, the actuators that drive the robot should in no way be damaged and should stop to change direction in case of insurmountable disturbances. In this context, two controllers are implemented and a comparative study is carried out to demonstrate the effectiveness of the proposed approaches. For the first one, neural networks are used to optimize the parameters of a PID controller and for the second a fuzzy inference system type Mamdani based controller is adopted. The goal is to implement control algorithms for safe robot navigation while avoiding damage to the motors. In these two control cases, the smart robot has to quickly perform tasks and adapt to changing environment conditions while ensuring stability and accuracy and must be autonomous with regards to decision making. Simulations results aren't done in real environments, but are obtained with the Matlab/Simulink environment in which holes and stones are modeled by different load torques and are applied as disturbances on the mobile robot environment. These simulation results and the robot performances are satisfactory and are compared to a PID controller in which parameters are tuned by the Ziegler–Nichols tuning method. The applied methods have proven to be highly robust.     

Dissipativity analysis of neural networks with time-varying delays

A new definition of dissipativity for neural networks is presented in this paper. By constructing proper Lyapunov functionals and using some analytic techniques, sufficient conditions are given to ensure the dissipativity of neural networks with or without time-varying parametric uncertainties and the integro-differential neural networks in terms of linear matrix inequalities. Numerical examples are given to illustrate the effectiveness of the obtained results.