Reliability-based approach to the inverse kinematics solution of robots using Elman's networks

The solution of inverse kinematics problem of redundant manipulators is a fundamental problem in robot control. The inverse kinematics problem in robotics is the determination of joint angles for a desired cartesian position of the end effector. For the solution of this problem, many traditional solutions such as geometric, iterative and algebraic are inadequate if the joint structure of the manipulator is more complex. Furthermore, many neural network approaches have been done to this problem. But the neural network-based solutions are not much reliable due to the error at the end of learning. Therefore, a reliability-based neural network inverse kinematics solution approach has been presented, and applied to a six-degrees of freedom (dof) robot manipulator in this paper. The structure of the proposed method is based on using three networks designed parallel to minimize the error of the whole system. Elman network, which has a profound impact on the learning capability and performance of the network, is chosen and designed according to the proposed solution method. At the end of parallel implementation, the results of each network are evaluated using direct kinematics equations to obtain the network with best result.     

A neural-network committee machine approach to the inverse kinematics problem solution of robotic manipulators

In robotics, inverse kinematics problem solution is a fundamental problem in robotics. Many traditional inverse kinematics problem solutions, such as the geometric, iterative, and algebraic approaches, are inadequate for redundant robots. Recently, much attention has been focused on a neural-network-based inverse kinematics problem solution in robotics. However, the result obtained from the neural network requires to be improved for some sensitive tasks. In this paper, a neural-network committee machine (NNCM) was designed to solve the inverse kinematics of a 6-DOF redundant robotic manipulator to improve the precision of the solution. Ten neural networks (NN) were designed to obtain a committee machine to solve the inverse kinematics problem using separately prepared data set since a neural network can give better result than other ones. The data sets for the neural-network training were prepared using prepared simulation software including robot kinematics model. The solution of each neural network was evaluated using direct kinematics equation of the robot to select the best one. As a result, the committee machine implementation increased the performance of the learning.     

多智能体专家型策略梯度的目标跟踪与清障

为适应复杂环境下目标跟踪机器人高效运动规划需求,本文提出一种基于多智能体强化学习的专家型策略梯度(ML-DDPG) 方法。为此首先构建了基于最小化任务单元的分布式多Actor-Critic网络架构;随后针对机器人主动障碍清除和目标跟踪任务建立了强化学习运动学模型和视觉样本预处理机制,由此提出一种专家型策略引导的最优目标价值估计方法;进一步通过并行化训练与集中式经验共享,提升了算法的训练效率;最后在不同任务环境下测试了ML-DDPG 算法的目标跟踪与清障性能表现,和其它算法对比验证了其在陌生环境中良好的迁移与泛化能力。     

A robust adaptive control of a parallel robot

The work presented in this article deals with the robust adaptive control tracking of a 6 degree of freedom parallel robot, called C5 parallel robot. The proposed approach is based on the coupling of sliding modes and multi-layers perceptron neural networks (MLP-NNs). It does not require the inverse dynamic model for deriving the control law. The MLP-NN is added in the control scheme to estimate the gravitational and frictional forces along with the non-modelled dynamic effects. The nonlinearity problem, present in neural networks, is resolved using Taylor series expansion. The proposed approach allows to adjust the parameters of neural network and sliding mode control terms by taking into account a reference model and the closed-loop stability in the Lyapunov sense. We implemented our approach on the C5 parallel robot of LISSI laboratory and performed experiments to observe its effectiveness and the robust behaviour of the controller against external disturbances.     

两级传感器信息融合的移动机器人避障研究

针对移动机器人的避障问题,以AS-R移动机器人为研究平台,提出了一种将神经网络和模糊神经网络相结合的两级融合方法。采用BP神经网络对多超声波传感器信息进行融合,以减少传感器信息的不确定,提高对障碍物识别的准确率;采用模糊神经网络实现移动机器人的避障决策控制,使之更适合系统的避障要求。该方法使移动机器人在避障中具有较好的灵活性和鲁棒性。机器人避障实验验证了所提方法的有效性。     

Neural Network Solution for Forward Kinematics Problem of Cable Robots

Forward kinematics problem of cable robots is very difficult to solve the same as that of parallel robots and in the contrary to the serial manipulators’. This problem is almost impossible to solve analytically because of the nonlinearity and complexity of the robot’s kinematic equations. Numerical methods are the most common solutions for this problem of the parallel and cable robots. But, convergency of these methods is the drawback of using them. In this paper, neural network approach is used to solve the forward kinematics problem of an exemplary 3D cable robot. This problem is solved in the typical workspace of the robot. The neural network used in this paper is of the MLP type and a back propagation procedure is utilized to train the network. A simulation study is performed and the results show the advantages of this method in enhancement of convergency together with very small modeling errors.     

Hybrid moment/position control of a parallel robot

In this paper, a hybrid moment/position controller in task space is proposed for tasks involving a contact between a robot and its environment. We consider a contour-tracking task performed by a six DOF (Degrees Of Freedom) parallel robot. The task space dynamic model of the robot in contact with its environment, seen as a black box, is estimated by a MLP-NN (MultiLayer Perceptron Neural Network). The neural network non-linearity is treated using Taylor series expansion. An adaptation algorithm of the neural parameters resulting from a closed-loop stability analysis is proposed. The performance of the proposed controller is validated on the C5 parallel robot by considering two different environments: rigid and compliant.     

机器人的模拟复合正交神经网络学习控制

提出一种神经网络与PD并行控制的机器人学习控制系统。为了加快神经网络的学习算法,在数字复合正交神经网络的基础上给出一种模拟复合正交神经网络的学习算法,以两关节机器人为对象仿真结果表明,该控制方法使机器人跟踪期望轨迹,其系统响应、跟踪精度和鲁棒性优于常规的控制方法,位置跟踪获得了满意的控制效果。该模拟神经控制器为不确定系统的控制提供了一种新的途径。     

基于改进型BP网络的并联机器人自适应力控制

并联机器人力控制是并联机器人研究的一个热点和难点,引起了许多学者的关注,并取得了一定的成果。多数使用了传统的力控制研究方法。该文中,作者将神经网络引入并联机器人的力控制中,并介绍了一种改进型BP神经网络,以及其学习算法和网络的训练过程,并结合实际并联机器人6-SPS并联机器人,设计出基于改进型BP神经网络的并联机器人自适应力控制器,并进行了仿真和实验研究,通过研究表明所设计的控制器是可行和有效的。     

一种新的基于广义细胞自动机的网络快速包交换优化方法

实时优化求解快速包交换问题(FPS)是提高网络性能的重要手段．基于梯度下降法等数学规划方法，不能并行地实时地优化求解FPS问题，而基于Hopfield型神经网络和细胞神经网络的优化方法中，都只有单一粒度的细胞动力学方程和单一粒度细胞之间的相互作用，不仅收敛到平衡点的过程长，而且神经网络参数的选择和修正十分困难．该文提出一种新的具有多粒度宏细胞的广义细胞自动机模型和方法，广义细胞自动机中的小粒度宏细胞聚合成可以独立演化的大粒度宏细胞，通过多粒度群体的不同程度群体智能的相互作用，能够比目前其他方法更快更有效地分布并行地优化求解FPS问题和其它类似的复杂的网络优化问题．     

Multiobjective Evolution of Neural Controllers and Task Complexity

Robots operating in everyday life environments are often required to switch between different tasks. While learning and evolution have been effectively applied to single task performance, multiple task performance still lacks methods that have been demonstrated to be both reliable and efficient. This paper introduces a new method for multiple task performance based on multiobjective evolutionary algorithms, where each task is considered as a separate objective function. In order to verify the effectiveness, the proposed method is applied to evolve neural controllers for the Cyber Rodent (CR) robot that has to switch properly between two distinctly different tasks: 1) protecting another moving robot by following it closely and 2) collecting objects scattered in the environment. Furthermore, the tasks and neural complexity are analyzed by including the neural structure as a separate objective function. The simulation and experimental results using the CR robot show that the multiobjective-based evolutionary method can be applied effectively for generating neural networks that enable the robot to perform multiple tasks simultaneously.     

Modelling of Complete Robot Dynamics Based on a Multi-Dimensional, RBF-like Neural Architecture

A neural network based identification approach of manipulator dynamics is presented. For a structured modelling, RBF-like static neural networks are used in order to represent and adapt all model parameters with their non-linear dependences on the joint positions. The neural architecture is hierarchically organised to reach optimal adjustment to structural apriori-knowledge about the identification problem. The model structure is substantially simplified by general system analysis independent of robot type. But also a lot of specific features of the utilised experimental robot are taken into account.A fixed, grid based neuron placement together with application of B-spline polynomial basis functions is utilised favourably for a very effective recursive implementation of the neural architecture. Thus, an online identification of a dynamic model is submitted for a complete 6 joint industrial robot.     

Finite-element neural networks for solving differential equations

The solution of partial differential equations (PDE) arises in a wide variety of engineering problems. Solutions to most practical problems use numerical analysis techniques such as finite-element or finite-difference methods. The drawbacks of these approaches include computational costs associated with the modeling of complex geometries. This paper proposes a finite-element neural network (FENN) obtained by embedding a finite-element model in a neural network architecture that enables fast and accurate solution of the forward problem. Results of applying the FENN to several simple electromagnetic forward and inverse problems are presented. Initial results indicate that the FENN performance as a forward model is comparable to that of the conventional finite-element method (FEM). The FENN can also be used in an iterative approach to solve inverse problems associated with the PDE. Results showing the ability of the FENN to solve the inverse problem given the measured signal are also presented. The parallel nature of the FENN also makes it an attractive solution for parallel implementation in hardware and software.     

Synthesis of Neural Networks and PID Control for Performance Improvement of Industrial Robots

In this article, an approach for improving the performance of industrialrobots using multilayer feedforward neural networks is presented. Thecontroller based on this approach consists of two main components: a PIDcontrol and a neural network. The function of the neural network is tocomplement the PID control for the specific purpose of improving theperformance of the system over time. Analytical and experimental resultsconcerning this synthesis of neural networks and PID control are presented.The analytical results assert that the performance of PID-controlledindustrial robots can be improved through proper utilization of the learningand generalization ability of neural networks. The experimental results,obtained through actual implementation using a commercial industrial robot,demonstrate the effectiveness of such control synthesis for practicalapplications. The results of this work suggest that neural networks could beadded to existing PID-controlled industrial robots for performanceimprovement.     

Vision-based path following by using a neural network Guidance System

This article describes a neural network controller for guidance of a robot arm, used to model some aspects of autonomous vehicle technology. The controller uses video images with adaptive view-angles for the sensory input, and the system was configured to simulate an autonomous vehicle guidance system on a flat terrain using a high-contrast guiding path. To demonstrate the feasibility of using neural networks in this type of application, an Intelledex 405 robot fitted with a video camera and associated vision system was used. Phase I of the project consisted of a single-speed implementation and limited network training. Phase II featured a multi-speed implementation using adaptively varied view-angles based on robot arm velocity. It was shown that the neural network controller was able to control the robot arm along a path composed of path segments unlike those with which it was trained. In addition it was shown that a multi-speed implementation with adaptive view angles improved system performance. © 1994 John Wiley & Sons, Inc.     

Kinematic analysis of a novel 3-DOF actuation redundant parallel manipulator using artificial intelligence approach

Kinematic analysis is one of the key issues in the research domain of parallel kinematic manipulators. It includes inverse kinematics and forward kinematics. Contrary to a serial manipulator, the inverse kinematics of a parallel manipulator is usually simple and straightforward. However, forward kinematic mapping of a parallel manipulator involves highly coupled nonlinear equations. Therefore, it is more difficult to solve the forward kinematics problem of parallel robots. In this paper, a novel three degrees-of-freedom (DOFs) actuation redundant parallel manipulator is introduced. Different intelligent approaches, which include the Multilayer Perceptron (MLP) neural network, Radial Basis Functions (RBF) neural network, and Support Vector Machine (SVM), are applied to investigate the forward kinematic problem of the robot. Simulation is conducted and the accuracy of the models set up by the different methods is compared in detail. The advantages and the disadvantages of each method are analyzed. It is concluded that ν-SVM with a linear kernel function has the best performance to estimate the forward kinematic mapping of a parallel manipulator.     

A parallel distributed control architecture for multiple robot systems using a network of microcomputers

This paper presents the design and implementation of a parallel distributed control architecture for industrial multiple robot systems. The design methodology is based on a concept of discrete states and actions, and a robotic task is represented as a sequence of primitive actions. For cooperative or exclusive tasks at the synchronous level of multiple robot systems, Petri net representation is applied, and discrete event-driven control is implemented as a data flow network of concurrent processes communicating with each other. Implementation of multiprocessing control on a microcomputer and a network of microcomputers is discussed.     

Massively parallel architectures for large scale neural networksimulations

A toroidal lattice architecture (TLA) and a planar lattice architecture (PLA) are proposed as massively parallel neurocomputer architectures for large-scale simulations. The performance of these architectures is almost proportional to the number of node processors, and they adopt the most efficient two-dimensional processor connections for WSI implementation. They also give a solution to the connectivity problem, the performance degradation caused by the data transmission bottleneck, and the load balancing problem for efficient parallel processing in large-scale neural network simulations. The general neuron model is defined. Implementation of the TLA with transputers is described. A Hopfield neural network and a multilayer perceptron have been implemented and applied to the traveling salesman problem and to identity mapping, respectively. Proof that the performance increases almost in proportion to the number of node processors is given.     

基于观测器的机械手神经网络自适应控制

提出了一种基于观测器的机械手神经网络自适应轨迹跟随控制器设计方法,这里机 械手的动力学非线性假设是未知的,并且假设机械手仅有关节角位置测量.文中采用一个线 性观测器重构机械手的关节角速度,用神经网络逼近修正的机械手动力学非线性,改进系统 的跟随性能.基于观测器的神经网络自适应控制器能够保证机械手角跟随误差和观测误差的 一致终结有界性以及神经网络权值的有界性,最后给出了机械手神经网络自适应控制器-观 测器设计的主要理论结果,并通过数字仿真验证了所提方法的性能.     

基于情感-时空信息的机器人服务自主认知及个性化选择

为了提高机器人的人机交互能力,针对家庭服务机器人在认知服务任务时往往忽略用户情感因素的弊端,提出了以用户情感为核心的机器人服务任务自主认知方法以及个性化服务选择策略.首先,利用智能空间本体技术结合用户情感状态与时间空间信息建立情感-时空本体模型,消除智能空间中的信息异构性.在此基础上,将与情感-时空相关的服务规则库编码并训练BP（逆向传播）神经网络构建推理机,将实时更新的智能空间信息与神经网络相匹配,推理出机器人需要执行的服务,实现机器人对以用户情感为核心的服务任务自主认知.最后,将用户情感状态作为执行服务的奖惩反馈信号,对服务集合中的子类服务进行动态的偏好度调节,完成有针对性的服务选择.仿真结果表明,基于该方法能够实现以用户情感为核心的机器人服务任务自主认知,同时可以根据用户偏好变化提供个性化的服务,有效提高了家庭服务机器人的智能性和灵活性,增强了用户的服务体验.