Cooperative neural field for the path planning of a robot arm

This paper deals with the problem of finding a good trajectory, from an initial position to a prescribed target point, for the end effector of a robot arm moving on a two-dimensional work field and avoiding obstacles lying on the work field. Two algorithms based on cooperative neural fields are proposed: the former is suited for the case where the location of obstacles is known, the latter doesn't require any a priori knowledge and is based on a very crude collision detector.     

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     

Evolutionary robot controllers with competitive and cooperative neural networks

This article describes a new approach for control systems for an autonomous mobile robot by using sandwiches of two different types of neural network. One is a neural network with competition and cooperation, and is used for recognizing sensor information where synaptic coupling are fixed. The second is a neural network with adaptive synaptic couplings corresponding to a genotype in a creature, and used for self-learning for the wheel controls. In a computer simulation model, we were successful in obtaining four types of robot with good performance when going along a wall. The model also showed robustness in a real environment. This work was presented, in part, at the Sixth International Symposium on Artificial Life and Robotics, Tokyo Japan, January 15–17, 2001     

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.     

Interactive robot trajectory planning and simulation using Augmented Reality

Human-robot interaction in industrial robotics has largely been confined to finding better ways to reconfigure or program the robots. In this paper, an Augmented Reality based (RPAR-II) system is proposed to facilitate robot programming and trajectory planning considering the dynamic constraints of the robots. Through the various simulation capabilities provided in the proposed AR environment, the users are able to preview the simulated motion, perceive any possible overshoot, and resolve discrepancies between the planned and simulated paths prior to the execution of a task. By performing the simulation, the performance of the trajectory planning and the fitness of the selection of the robot controller model/parameters in the robot programming process can be visually evaluated. Practical issues concerning the system implementation are also discussed.     

Time-optimal and jerk-continuous trajectory planning for robot manipulators with kinematic constraints

In this paper a high smooth trajectory planning method is presented to improve the practical performance of tracking control for robot manipulators. The strategy is designed as a combination of the planning with multi-degree splines in Cartesian space and multi-degree B-splines in joint space. Following implementation, under the premise of precisely passing the via-points required, the cubic spline is used in Cartesian space planning to make either the velocities or the accelerations at the initial and ending moments controllable for the end effector. While the septuple B-spline is applied in joint space planning to make the velocities, accelerations and jerks bounded and continuous, with the initial and ending values of them configurable. In the meantime, minimum-time optimization problem is also discussed. Experimental results show that, the proposed approach is an effective solution to trajectory planning, with ensuring a both smooth and efficiency tracking performance with fluent movement for the robot manipulators.     

Using FORTH to control a robot arm

The characteristics of the Cyber 3 robot arm are outlined, with a brief history of programming languages used to control it. The advantages of FORTH over its rivals are given. A program sequence for a robot to reorient an object is given.     

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.     

Multiple fuzzy state-value functions for human evaluation through interactive trajectory planning of a partner robot

The purpose of this study is to develop partner robots that can obtain and accumulate human-friendly behaviors. To achieve this purpose, the entire architecture of the robot is designed, based on a concept of structured learning which emphasizes the importance of interactive learning of several modules through interaction with its environment. This paper deals with a trajectory planning method for generating hand-to-hand behaviors of a partner robot by using multiple fuzzy state-value functions, a self-organizing map, and an interactive genetic algorithm. A trajectory for the behavior is generated by an interactive genetic algorithm using human evaluation. In order to reduce human load, human evaluation is estimated by using the fuzzy state-value function. Furthermore, to cope with various situations, a self-organizing map is used for clustering a given task dependent on a human hand position. And then, a fuzzy state-value function is assigned to each output unit of the self-organizing map. The robot can easily obtain and accumulate human-friendly trajectories using a fuzzy state-value function and a knowledge database corresponding to the unit selected in the self-organizing map. Finally, multiple fuzzy state-value functions can estimate a human evaluation model for the hand-to-hand behaviors. Several experimental results show the effectiveness of the proposed method.     

Ripple reduction at speed and torque of step motors used on a two-axis robot arm

This paper presents the control of two axis robot arm. The system is consisted of two step motors, robot arm, computer and PIC16F84A. One of them controls the robot arm via parallel port of the computer. The other one controls end element on the arm by PIC16F84A. PIC16F84A drives the motor by the designed circuit drive. Although the control of the step motor is very easy, they work choppily. Therefore, it is necessary to reduce the ripples occurred at the speed and torque of the step motor. In this study, proportional–integral–derivative (PID) controller is used to reduce the ripples. The obtained results show the proposed method is very successful.     

Novel integrated optimization algorithm for trajectory planning of robot manipulators based on integrated evolutionary programming

Optimal trajectory plarmmg for robot manipulators plays an important role in implementing the high productivity for robots. The performance indexes used in optimal trajectory planning are classified into two roam categories:optimum traveling time and optimum mechanical energy of the actuators. The current trajectory planning algorithms are designed based on one of the above two performance indexes. So far, there have been few planning algorithms designed to satisfy two performance indexes simultaneously. On the other hand, some deficiencies arise in the existing integrated optimization algorithms of trajectory planning.In order to overcome those deficiencies, the integrated optimization algorithms of trajectory planning are presented based on the complete analysis for trajectory planning of robot manipulators. In the algorithm, two object functiom are designed based on the specific weight coefficient method and “ideal point” strategy. Moreover, based on the features of optimization problem, the intensified evolutionary programming is proposed to solve the corresponding optimization model. Especially, for the Stanford Robot, the high-quality solutions are found at a lower cost.     

ESN网络在机器人轨迹跟踪控制中的应用

为了研究具有模型不确定性的机器人操作手的轨迹跟踪控制,采用一种新的递归神经网络——回声状态网络(ESN)设计了动态控制器.采用PID控制器补偿ESN网络的逆建模误差,并在网络训练过程中加入白噪声项,以保证动态系统的稳定性.最后针对两关节机械手的轨迹跟踪控制问题进行了数值仿真,仿真结果表明了该方法的有效性.     

Application of a neural network to improve an automated thermoplastic tow-placement process

This study demonstrates the use of an on-line neural network to calculate process set points for PID controllers in a manufacturing process such as the automated thermoplastic tow-placement (ATP) technique. The set points are computed by the neural network so that the throughput is near maximum and a desired minimum quality is maintained. A novel neural network predictive scheme is developed to enable performance over a wide range of processing inputs. Process history can greatly affect the final part quality and, therefore, is an integral part of the method for determining the set points. The system is first trained and tested in simulation and then validated for the highly non-linear ATP process resulting in significantly improved process operation. The developed approach is applicable to many other manufacturing processes where process simulations exist and conventional control techniques are lacking.     

BP神经网络在智能车辆方向控制中的应用

驾驶员模型是智能控制中复杂的控制系统,方向控制是其核心部分。本文建立了一种基于侧向距离偏差的前视轨迹驾驶员模型。并利用神经网络的学习功能设计了一种基于BP神经网络的汽车行驶方向控制器,仿真试验表明该设计可行有效。     

Combination of the assembly neural network with a perceptron for recognition of handwritten digits arranged in numeral strings

The purpose of the paper is to design and test neural network structures and mechanisms for making use of the information that is contained in the character strings for more correct recognition of the characters constituting these strings. Two neural networks are considered in the paper; both networks are combined into a joint recognition system. The first is the assembly neural network and the second is the neural network of a perceptron type. A computer simulation of the system is performed. The combined system solves the task of recognition of handwritten digits of the MNIST test set provided that the digits have been arranged in the numeral strings memorized in the system. During a recognition process of an input numeral string, the assembly neural network executes intermediate recognition of the digits basing on which a perceptron type network accomplishes the final choice among the limited combinations of strings memorized in the network. The experiments have demonstrated that the combined system is able to make use of the information that is contained in the strings for more correct recognition of digits of the MNIST test set. In particular, the experiments have shown that the combined system commits no errors in the recognition of MNIST test set on the condition that the digits of this set had been organized in the strings of more than 5 digits each.     

Timed trajectory generation using dynamical systems: Application to a Puma arm

We present an attractor based dynamics that autonomously generates trajectories with stable timing (limit cycle solutions), stably adapted to changing online sensory information. Autonomous differential equations are used to formulate a dynamical layer with either stable fixed points or a stable limit cycle. A neural competitive dynamics switches between these two regimes according to sensorial context and logical conditions. The corresponding movement states are then converted by simple coordinate transformations and an inverse kinematics controller into spatial positions of a robot arm. Movement initiation and termination is entirely sensor driven. In this article, the dynamic architecture was changed in order to cope with unreliable sensor information by including this information in the vector field.We apply this architecture to generate timed trajectories for a Puma arm which must catch a moving ball before it falls over a table, and return to a reference position thereafter. Sensory information is provided by a camera mounted on the ceiling over the robot. A flexible behavior is achieved. Flexibility means that if the sensorial context changes such that the previously generated sequence is no longer adequate, a new sequence of behaviors, depending on the point at which the changed occurred and adequate to the current situation emerges.The evaluation results illustrate the stability and flexibility properties of the dynamical architecture as well as the robustness of the decision-making mechanism implemented.     

Qubit neural network and its learning efficiency

Neural networks have attracted much interest in the last two decades for their potential to realistically describe brain functions, but so far they have failed to provide models that can be simulated in a reasonable time on computers; rather they have been limited to toy models. Quantum computing is a possible candidate for improving the computational efficiency of neural networks. In this framework of quantum computing, the Qubit neuron model, proposed by Matsui and Nishimura, has shown a high efficiency in solving problems such as data compression. Simulations have shown that the Qubit model solves learning problems with significantly improved efficiency as compared to the classical model. In this paper, we confirm our previous results in further detail and investigate what contributes to the efficiency of our model through 4-bit and 6-bit parity check problems, which are known as basic benchmark tests. Our simulations suggest that the improved performance is due to the use of superposition of neural states and the use of probability interpretation in the observation of the output states of the model.     

A neural network based adaptive robot controller

Neural network based adaptive controllers have been shown to achieve much improved accuracy compared with traditional adaptive controllers when applied to trajectory tracking in robot manipulators. This paper describes a new Recursive Prediction Error technique for estimating network parameters which is more computationally efficient. Results show that this neural controller suppresses disturbances accurately and achieves very small errors between commanded and actual trajectories.