基于解析法和遗传算法的机械手运动学逆解

研究优化机械手轨迹规划问题,机械手运动时要具有稳定性避障性能。针对平面3自由度冗余机械手优化控制问题,建立机械手的结构模型。提出用解析法和遗传算法相结合满足具有计算量小和适应性强的特点。在给定机械手末端执行器的运动轨迹,按着机械手冗余自由度,运动轨迹上每个点对应的关节角有无穷多个解。而通过算法可以找到一组最优的关节角,可得到优化机械手运动过程中柔顺性和避障点。仿真结果表明,该算法可以快速收敛到全局最优解,可用于计算冗余机械手运动学逆解,并可实现机器人的轨迹规划和避障优化控制。     

Obstacle avoidance for kinematically redundant manipulators using a dual neural network.

One important issue in the motion planning and control of kinematically redundant manipulators is the obstacle avoidance. In this paper, a recurrent neural network is developed and applied for kinematic control of redundant manipulators with obstacle avoidance capability. An improved problem formulation is proposed in the sense that the collision-avoidance requirement is represented by dynamically-updated inequality constraints. In addition, physical constraints such as joint physical limits are also incorporated directly into the formulation. Based on the improved problem formulation, a dual neural network is developed for the online solution to collision-free inverse kinematics problem. The neural network is simulated for motion control of the PA10 robot arm in the presence of point and window-shaped obstacle.     

Robot arm reaching through neural inversions and reinforcement learning

We present a neural method that computes the inverse kinematics of any kind of robot manipulators, both redundant and non-redundant. Inverse kinematics solutions are obtained through the inversion of a neural network that has been previously trained to approximate the manipulator forward kinematics. The inversion provides difference vectors in the joint space from difference vectors in the workspace. Our differential inverse kinematics (DIV) approach can be viewed as a neural network implementation of the Jacobian transpose method for arm kinematic control that does not require previous knowledge of the arm forward kinematics. Redundancy can be exploited to obtain a special inverse kinematic solution that meets a particular constraint (e.g. joint limit avoidance) by inverting an additional neural network The usefulness of our DIV approach is further illustrated with sensor-based multilink manipulators that learn collision-free reaching motions in unknown environments. For this task, the neural controller has two modules: a reinforcement-based action generator (AG) and a DIV module that computes goal vectors in the joint space. The actions given by the AG are interpreted with regard to those goal vectors.     

Trajectory Planning with Collision Avoidance for Redundant Robots Using Jacobian and Artificial Potential Field-based Real-time Inverse Kinematics

This study proposes an algorithm for combining the Jacobian-based numerical approach with a modified potential field to solve real-time inverse kinematics and path planning problems for redundant robots in unknown environments. With an increase in the degree of freedom (DOF) of the manipulator, however, the problems in realtime inverse kinematics become more difficult to solve. Although the analytical and geometrical inverse kinematics approach can obtain the exact solution, it is considerably difficult to solve as the DOF increases, and it necessitates recalculations whenever the robot arm DOF or Denavit-Hartenberg (D-H) parameters change. In contrast, the numerical method, particularly the Jacobian-based numerical method, can easily solve inverse kinematics irrespective of the aforementioned changes including those in the robot shape. The latter method, however, is not employed in path planning for collision avoidance, and it presents real-time calculation problems. This study accordingly proposes the Jacobian-based numerical approach with a modified potential field method that can realize real-time calculations of inverse kinematics and path planning with collision avoidance irrespective of whether the case is redundant or non-redundant. To achieve this goal, the use of a judgment matrix is proposed for obstacle condition identification based on the obstacle boundary definition; an approach for avoiding the local minimum is also proposed. After the obstacle avoidance path is generated, a trajectory plan that follows the path and avoids the obstacle is designed. Finally, the proposed method is evaluated by implementing a motion planning simulation of a 7-DOF manipulator, and an experiment is performed on a 7-DOF real robot.

     

A fast approach for the robust trajectory planning of redunant robot manipulators

In this article, a fast approach for robust trajectory planning, in the task space, of redundant robot manipulators is presented. The approach is based on combining an original method for obstacle avoidance by the manipulator configuration with the traditional potential field approach for the motion planning of the end-effector. This novel method is based on formulating an inverse kinematics problem under an inexact context. This procedure permits dealing with the avoidance of obstacles with an appropriate and easy to compute null space vector; whereas the avoidance of singularities is attained by the proper pseudoinverse perturbation. Furthermore, it is also shown that this formulation allows one to deal effectively with the local minimum problem frequently associated with the potential field approaches. The computation of the inverse kinematics problem is accomplished by numerically solving a linear system, which includes the vector for obstacle avoidance and a scheme for the proper pseudoinverse perturbation to deal with the singularities and/or the potential function local minima. These properties make the proposed approach suitable for redundant robots operating in real time in a sensor-based environment. The developed algorithm is tested on the simulation of a planar redundant manipulator. From the results obtained it is observed that the proposed approach compares favorably with the other approaches that have recently been proposed. © 1995 John Wiley & Sons, Inc.     

State-chain sequential feedback reinforcement learning for path planning of autonomous mobile robots

This paper deals with a new approach based on Q-learning for solving the problem of mobile robot path planning in complex unknown static environments.As a computational approach to learning through interaction with the environment,reinforcement learning algorithms have been widely used for intelligent robot control,especially in the field of autonomous mobile robots.However,the learning process is slow and cumbersome.For practical applications,rapid rates of convergence are required.Aiming at the problem of slow convergence and long learning time for Q-learning based mobile robot path planning,a state-chain sequential feedback Q-learning algorithm is proposed for quickly searching for the optimal path of mobile robots in complex unknown static environments.The state chain is built during the searching process.After one action is chosen and the reward is received,the Q-values of the state-action pairs on the previously built state chain are sequentially updated with one-step Q-learning.With the increasing number of Q-values updated after one action,the number of actual steps for convergence decreases and thus,the learning time decreases,where a step is a state transition.Extensive simulations validate the efficiency of the newly proposed approach for mobile robot path planning in complex environments.The results show that the new approach has a high convergence speed and that the robot can find the collision-free optimal path in complex unknown static environments with much shorter time,compared with the one-step Q-learning algorithm and the Q(λ)-learning algorithm.     

Inverse kinematics of variable-geometry truss manipulators

A new class of robotic arm consists of a periodic sequence of truss substructures, each of which has several variable-length members. Such variable-geometry truss manipulators (VGTMs) are inherently highly redundant and promise a significant increase in dexterity over conventional anthropomorphic manipulators. This dexterity may be exploited for both obstacle avoidance and controlled deployment in complex workspaces. The inverse kinematics problem for such unorthodox manipulators, however, becomes complex because of the large number of degrees of freedom, and conventional solutions to the inverse kinematics problem become inefficient because of the high degree of redundancy. This paper presents a solution to this problem based on a spline-like reference curve for the manipulator's shape. Such an approach has a number of advantages: (1) direct, intuitive manipulation of shape; (2) reduced calculation time; and (3) direct control over the effective degree of redundancy of the manipulator. Furthermore, although the algorithm has been developed primarily for variable-geometry-truss manipulators, it is general enough for application to other manipulator designs.     

An efficient local approach for the path generation of robot manipulators

In this article an efficient local approach for the path generation of robot manipulators is presented. The approach is based on formulating a simple nonlinear programming problem. This problem is considered as a minimization of energy with given robot kinematics and subject to the robot requirements and a singularities avoidance constraint. From this formulation a closed form solution is derived which has the properties that allows to pursue both singularities and obstacle avoidance simultaneously; and that it can incorporate global information. These properties enable the accomplishment of the important task that while a specified trajectory in the operational space can be closely followed, also a desired joint configuration can be attained accurately at a given time. Although the proposed approach is primarily developed for redundant manipulators, its application to nonredundant manipulators is examplified by considering a particular commercial manipulator.     

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.     

冗余机械臂逆运动学求解方法研究进展

随着科学技术的发展,冗余机械臂凭借其多自由度的特性获得学者的广泛关注.其中包括执行指定任务时,需要将任务路径转换为关节空间轨迹,进行逆运动学求解,求取非线性函数的连续逆映射.该求解过程尤为重要且非常复杂,国内外学者对此开展了大量研究.这里将冗余机械臂逆运动学求解方法进行分类,归纳整理出各类求解方法,分别概述解析法、数值解法、智能算法以及对应子方法的基本原理、对比及研究现状.最后,指出逆运动学求解方法面临的核心问题以及发展趋势.     

A geometric approach for inverse kinematics of a 4-link redundant In-Vivo robot for biopsy

The presence of a large number of degrees of freedom enables redundant manipulators to have some desirable features like reaching difficult areas and avoiding obstacles. These manipulators in the form of In-Vivo robots will enhance the dexterity and capacity of a surgeon to explore the internal cavity when inserted in the existing tool channel of the endoscope to take a biopsy from the stomach. This paper presents a simple geometric approach, to solve the problem of multiple inverse kinematic solutions of redundant manipulators, to find a single optimum solution and to easily switch from one solution to another depending upon the path and the environment. A simulation model of this approach has been developed and experiments have been conducted on the In-Vivo robot to judge its effectiveness.     

An Artificial Neural Network Approach for Inverse Kinematics Computation and Singularities Prevention of Redundant Manipulators

In this article an Artificial Neural Network (ANN) approach for fast inverse kinematics computation and effective singularities prevention of redundant robot manipulators is presented. The approach is based on establishing some characterizing matrices, representing some geometrical concepts, in order to yield a simple performance index and a null space vector for singularities avoidance/prevention and safe path generation. Here, this null space vector is computed using a properly trained ANN and included in the computation of the inverse kinematics being performed also by another properly trained ANN.     

Probabilistic neural network training procedure based on Q(0)-learning algorithm in medical data classification

In this article, an iterative procedure is proposed for the training process of the probabilistic neural network (PNN). In each stage of this procedure, the Q(0)-learning algorithm is utilized for the adaptation of PNN smoothing parameter (σ). Four classes of PNN models are regarded in this study. In the case of the first, simplest model, the smoothing parameter takes the form of a scalar; for the second model, σ is a vector whose elements are computed with respect to the class index; the third considered model has the smoothing parameter vector for which all components are determined depending on each input attribute; finally, the last and the most complex of the analyzed networks, uses the matrix of smoothing parameters where each element is dependent on both class and input feature index. The main idea of the presented approach is based on the appropriate update of the smoothing parameter values according to the Q(0)-learning algorithm. The proposed procedure is verified on six repository data sets. The prediction ability of the algorithm is assessed by computing the test accuracy on 10 %, 20 %, 30 %, and 40 % of examples drawn randomly from each input data set. The results are compared with the test accuracy obtained by PNN trained using the conjugate gradient procedure, support vector machine algorithm, gene expression programming classifier, k–Means method, multilayer perceptron, radial basis function neural network and learning vector quantization neural network. It is shown that the presented procedure can be applied to the automatic adaptation of the smoothing parameter of each of the considered PNN models and that this is an alternative training method. PNN trained by the Q(0)-learning based approach constitutes a classifier which can be treated as one of the top models in data classification problems.     

Obstacle Avoidance for Spatial Hyper‐Redundant Manipulators Using Harmonic Potential Functions and the Mode Shape Technique

This paper deals with the obstacle avoidance problem for spatial hyper‐redundant manipulators in known environments. The manipulator is divided into two sections, a proximal section that has not entered the space among the obstacles and a distal section among the obstacles. Harmonic potential functions are employed to achieve obstacle avoidance for the distal section in three‐dimensional space in order to avoid local minima in cluttered environments. A modified panel method is used to generate the potential of any arbitrary shaped obstacle in three‐dimensional space. An alternative backbone curve concept and an efficient fitting method are introduced to control the trajectory of proximal links. The fitting method is recursive and avoids the complications involved with solving large systems of nonlinear algebraic equations. The combination of a three‐dimensional safe path derived from the harmonic potential field and the backbone curve concept leads to an elegant kinematic control strategy that guarantees obstacle avoidance. © 2003 Wiley Periodicals, Inc.     

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.     

Learning Dynamic Obstacle Avoidance for a Robot Arm Using Neuroevolution

Neural networks can be evolved to control robot manipulators in tasks like target tracking and obstacle avoidance in complex environments. Neurocontrollers are robust to noise and can be adapted to different environments and robot configurations. In this paper, neurocontrollers were evolved to position the end effector of a robot arm close to a target in three different environments: environments without obstacles, environments with stationary obstacles, and environments with moving obstacles. The evolved neurocontrollers perform qualitatively like inverse kinematic controllers in environments with no obstacles and like path-planning controllers based on Rapidly-exploring random trees in environments with obstacles. Unlike inverse kinematic controllers and path planners, the approach reliably generalizes to environments with moving obstacles, making it possible to use it in natural environments.     

A neuro-genetic-simulated annealing approach to the inverse kinematics solution of robots: a simulation based study

In this study, a hybrid intelligent solution system including neural networks, genetic algorithms and simulated annealing has been proposed for the inverse kinematics solution of robotic manipulators. The main purpose of the proposed system is to decrease the end effector error of a neural network based inverse kinematics solution. In the designed hybrid intelligent system, simulated annealing algorithm has been used as a genetic operator to decrease the process time of the genetic algorithm to find the optimum solution. Obtained best solution from the neural network has been included in the initial solution of genetic algorithm with randomly produced solutions. The end effector error has been reduced micrometer levels after the implementation of the hybrid intelligent solution system.     

Obstacle Avoidance for Redundant Manipulators Using Directional-Collidability/ Temporal-Collidability Measure

We present an efficient obstacle avoidance control algorithm for redundant manipulators using new measures called directional-collidability measure and temporal-collidability measure. Considering relative movements of manipulator links and obstacles, the directional-collidability/temporal-collidability measure is defined as the sum of inverse of predicted collision distances/times between manipulator links and obstacles. These measures are suitable for obstacle avoidance control since relative velocities between manipulator links and obstacles are as important as distances between them. Also, we present a velocity-bounded kinematic control law which allows reasonably large gain to improve the system performance. Simulation results are presented to illustrate the effectiveness of the proposed algorithm.     

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.     

基于神经网络的冗余度TT-VGT机器人的运动学求解

应用BP神经网络对冗余度TT-VGT机器人的位姿正解进行训练学习,进而求解机器人 的位姿反解问题．根据网络模型求得机器人的一、二阶影响系数,应用神经网络求解雅可比 矩阵的伪逆．并对七重四面体的变几何桁架机器人进行了仿真计算．