Task-space neuro-sliding mode control of robot manipulators under Jacobian uncertainties

Cartesian robot control is an appealing scheme because it avoids the computation of inverse kinematics, in contrast to joint robot control approach. For tracking, high computational load is typically required to obtain Cartesian robot dynamics. In this paper, an alternative approach for Cartesian tracking is proposed under assumption that robot dynamics is unknown and the Jacobian are uncertain. A neuro-sliding second order mode controller delivers a low dimensional neural network, which roughly estimates inverse robot dynamics, and an inner smooth control loop guarantees exponential tracking. Experimental results are presented to confirm the performance in a real time environment.     

Comparison of RBF and MLP neural networks to solve inverse kinematic problem for 6R serial robot by a fusion approach

In this paper, a fusion approach to determine inverse kinematics solutions of a six degree of freedom serial robot is proposed. The proposed approach makes use of radial basis function neural network for prediction of incremental joint angles which in turn are transformed into absolute joint angles with the assistance of forward kinematics relations. In this approach, forward kinematics relations of robot are used to obtain the data for training of neural network as well to estimate the deviation of predicted inverse kinematics solution from the desired solution. The effectiveness of the fusion process is shown by comparing the inverse kinematics solutions obtained for an end-effector of industrial robot moving along a specified path with the solutions obtained from conventional neural network approaches as well as iterative technique. The prominent features of the fusion process include the accurate prediction of inverse kinematics solutions with less computational time apart from the generation of training data for neural network with forward kinematics relations of the robot.     

A New Geometric Subproblem to Extend Solvability of Inverse Kinematics Based on Screw Theory for 6R Robot Manipulators

Geometric inverse kinematics procedures that divide the whole problem into several subproblems with known solutions, and make use of screw motion operators have been developed in the past for 6R robot manipulators. These geometric procedures are widely used because the solutions of the subproblems are geometrically meaningful and numerically stable. Nonetheless, the existing subproblems limit the types of 6R robot structural configurations for which the inverse kinematics can be solved. This work presents the solution of a novel geometric subproblem that solves the joint angles of a general anthropomorphic arm. Using this new subproblem, an inverse kinematics procedure is derived which is applicable to a wider range of 6R robot manipulators. The inverse kinematics of a closed curve were carried out, in both simulations and experiments, to validate computational cost and realizability of the proposed approach. Multiple 6R robot manipulators with different structural configurations were used to validate the generality of the method. The results are compared with those of other methods in the screw theory framework. The obtained results show that our approach is the most general and the most efficient.

     

改进末端跟随运动的超冗余蛇形臂机器人运动学逆解

针对超冗余蛇形臂机器人运动学逆解中计算量大、超关节极限和位形偏移量大的问题,提出了一种改进末端跟随运动的逆解算法．在末端跟随法中引入蛇形臂弯曲角度的约束,调整关节位置的更新方式,使关节在蛇形臂轴线上运动．通过依次更新关节的空间位置,将超冗余多节蛇形臂的运动学逆解转化为2自由度单节蛇形臂的运动学逆解．仿真分析了蛇形臂机器人在基座移动和基座固定条件下的轨迹跟踪效果,对比了同一目标位置下不同方法的性能．结果表明,改进后的算法能保证蛇形臂的弯曲角度不超过给定范围,关节的运动量从末端到基座依次减小,机器人的运动更协调;与基于雅可比矩阵的数值法和现有启发式方法相比,该方法运算量降低,机器人整体位形偏移量减小,能用于蛇形臂机器人的实时控制．     

基于改进天牛须算法的电力攀爬机器人运动学逆解算法

为了提高电力系统的自动化水平,减轻电力工人在检修高压输电系统时的劳动强度,同时保障电力工人人身安全,提出并设计一种可以攀爬电力铁塔的六自由度关节式机器人,针对该构型进行运动学分析和求解.为解决传统的解析法用于机械臂逆运动学求解过程中存在操作繁琐和奇异点无法逆运算等问题,提出一种基于改进天牛须算法的电力攀爬机器人运动学逆解算法.首先,对电力攀爬机器人进行DH建模,得到正运动学方程;然后,使用正运动学方程和目标位姿建立代价函数,采用改进天牛须算法对代价函数优化;最后,使用Matlab实现此算法进行仿真验证.实验结果表明,与传统的天牛须算法、改进遗传算法以及改进粒子群算法相比,所提出算法具有较好的收敛性,求解精度较高.     

软实时环境下机器人运动学逆解研究

为有效抑制串联机构的末端振动,使机器人运动系统的运行更加平滑,设计了以PC104为硬件基础、在RTLinux上进行二次软件开发的机器人控制系统。它通过PCI/ISA总线连接上位机和底层硬件接口电路,以控制伺服电机。分别研究了机器人系统的模型,以及在这一软实时系统上采用反变换法+Pieper方法求解机器人的逆运动学问题。通过比较工业机器人在伺服控制、板卡控制和软件控制三种模式下的运动性能,验证了软件方式的优越性,以及其在运动控制领域中的应用价值。     

仿尺蠖爬壁机器人自适应吸附及摇杆控制

为了解决真空吸附爬壁机器人爬行时,需要吸盘和壁面紧密贴合,不易操控的问题。建立了吸盘足至壁面的空间几何模型;基于D-H参数,建立了运动学模型,根据速度运动学逆解,设计了一种用于对称机构爬壁机器人的摇杆操作方法,将摇杆轴映射为关节速度闭环;根据位置运动学逆解,设计了自适应吸附动作,吸盘足与壁面距离小于设定阈值时,自动触发自适应吸附动作;搭建了机器人控制系统和自适应吸附装置,在水平壁面上进行爬行实验,验证了该方法可减小操控难度。     

Extended Jacobian inverse kinematics algorithm for nonholonomic mobile robots

By a generalization of the well-known extended Jacobian method for stationary manipulators, we derive the extended Jacobian inverse kinematics algorithm for nonholonomic mobile robots. Key points of the derivation consist in defining the kinematics of a mobile robot as the end-point map of a driftless control system, decomposing the space of control functions of this system into a finite and an infinite dimensional subspaces, and introducing an augmenting kinematics map subordinated to this decomposition. The original kinematics and the augmenting kinematics constitute the extended kinematics. The inverse Jacobian of the extended kinematics defines the extended Jacobian inverse kinematics algorithm. By design, the algorithm is repeatable. As an example, we derive a specific extended Jacobian inverse kinematics algorithm and illustrate its performance with the computer simulations.     

Towards fully automatic reliable 3D acquisition: From designing imaging network to a complete and accurate point cloud

This paper describes a novel system for accurate 3D digitization of complex objects. Its main novelties can be seen in the new approach, which brings together different systems and tools in a unique platform capable of automatically generating an accurate and complete model for an object of interest. This is performed through generating an approximate model of the object, designing a stereo imaging network for the object with this model and capturing the images at the designed postures through exploiting an inverse kinematics method for a non-standard six degree of freedom robot. The images are then used for accurate and dense 3D reconstruction using photogrammetric multi-view stereo method in two modes, including resolving scale with baseline and with control points. The results confirm the feasibility of using Particle Swarm Optimization in solving inverse kinematics for this non-standard robot. The system provides this opportunity to test the effect of incidence angle on imaging network design and shows that the matching algorithms work effectively for incidence angle of 10°. The accuracy of the final point cloud generated with the system was tested in two modes through a comparison with a dataset generated with a close range 3D colour laser scanner.     

A Heuristic Approach to the Inverse Differential Kinematics Problem

Inversion of the kinematics of manipulators is one of the central problems in the field of robot arm control. The iterative use of inverse differential kinematics is a popular method of solving this task. Normally the solution of the problem requires a complex mathematical apparatus. It involves methods for solving equation systems as well as algorithms for optimization. In this paper we introduce a naïve heuristic method which works without the need for complex mathematical algorithms. This method forms a simple basis for the more sophisticated control procedures of our robot manipulator (JANUS).     

基于ReLU神经网络的移动目标视觉伺服研究

针对移动目标跟踪以及抓取的问题,提出一种基于ReLU网络模型的单目视觉伺服系统。首先建立机器人视觉系统,完成对目标跟踪以及特征提取的任务,并通过结合单目视觉模型对其位姿进行估计,从而得到目标状态;然后,利用ReLU神经网络对机械臂的逆运动学进行学习,并用训练后网络模型构建单目视觉伺服系统的控制策略来避免机器人逆运动学求解计算量大、多解等问题;最后,为了提高抓取成功率,对末端执行器的运动轨迹进行规划。实验在NAO机器人平台上进行,根据实验结果证明方法的有效性。     

A Real-Time Kinematics on the Translational Crawl Motion of a Quadruped Robot

It is known that the kinematics of a quadruped robot is complex due to its topology and the redundant actuation in the robot. However, it is fundamental to compute the inverse and direct kinematics for the sophisticated control of the robot in real-time. In this paper, the translational crawl gait of a quadruped robot is introduced and the approach to find the solution of the kinematics for such a crawl motion is proposed. Since the resulting kinematics is simplified, the formulation can be used for the real-time control of the robot. The results of simulation and experiment shows that the present method is feasible and efficient.     

约束条件下的巡线机器人逆运动学求解

高压输电线路巡检机器人是一种多关节悬挂运动机构,要实现其运动控制就需要根据机器人的本身机构特点和悬挂系统的运动约束条件进行运动学分析.本文利用微分扭转法对巡线机器人的正向运动学进行了求解,并通过对机器人悬挂系统的力学分析,得到了机器人运动学的约束条件,并在这种约束条件下,采用了一种可用来进行实时控制的迭代循环坐标下降(CCD)算法,来进行机器人的逆运动学求解.这种迭代算法对于有运动约束系统的逆运动学求解具有较强的适用性,而且它具有较好的收敛性和有效性,适合于在线计算,便于巡线机器人的实时运动控制.     

五轮铰接式月球机器人的运动学建模

本文为在有壕沟、台阶和斜坡的复杂三维地形上行驶的轮式移动机器人提出了一种新 的运动学建模方法：切平面拼接法．该方法的主要思想是用机器人在不同时刻不同斜面上的 运动学模型组成机器人在崎岖不平地面上行驶的复合运动学模型．该建模方法简单,建模的 精确性可以控制．作者用该方法建立了五轮铰接式月球机器人（FWALR）在崎岖不平地面上 行驶的正向和逆向运动学模型,为FWALR机器人在复杂三维地形上的运动控制奠定了基础．     

Recursive modelling in dynamics of Agile Wrist spherical parallel robot

Recursive matrix relations for kinematics and dynamics of the 3-RRR Agile Wrist spherical parallel robot are established in this paper. The prototype of the robot is a three-degrees-of-freedom mechanism with three identical legs. Controlled by concurrent torques, which are generated by some electric motors, the active elements of the robot have three independent rotations. Knowing the rotation motion of the moving platform, we develop first the inverse kinematical problem and determine the velocities and accelerations. Further, the principle of virtual work is used in the inverse dynamic problem. Matrix equations offer iterative expressions and graphs for the power requirement comparison of each of three actuators in two computational complexities: complete dynamic model and simplified dynamic model.     

General-purpose inverse kinematics transformations for robotic manipulators

Real-time robot control requires efficient inverse kinematics transformations to compute the temporal evolution of the joint coordinates from the motion of the end-effector. The development of a coherent, general-purpose framework, incorporating position, velocity and acceleration transformations, is the theme of this paper. In this framework, the computational requirements of a new inverse kinematic algorithm are delineated. The algorithm is applicable to serial (open-chain) manipulators with arbitrary axes of motion. Comparative evaluations of the computational cost of the algorithm demonstrate its efficacy and feasibility for real-time applications.     

3-RRRT并联机器人位置正向求解研究

研究一种3-RRRT型并联机器人机构的运动学正向求解方法。根据3-RRRT型并联机器人机构特点以及关节运动的取值范围，提出了以并联机器人支链中支杆的方向余弦和动平台绝对位置坐标为系统的广义坐标的方法，并详细地推导了3-RRRT型并联机器人运动学模型，通过进一步消除中间变量的方法最终获得了易于正、逆运动学求解的只包含3个驱动关节坐标与动平台3个绝对位置坐标的约束方程组。最后，运用基于Moore—Penwse广义逆的牛顿迭代格式编制了MATLAB运动学正向求解程序，并进行了运动学正向求解数值仿真，结果表明求解程序快速有效。     

An improved approach to the solution of inverse kinematics problems for robot manipulators

A structured artificial neural-network (ANN) approach has been proposed here to control the motion of a robot manipulator. Many neural-network models use threshold units with sigmoid transfer functions and gradient descent-type learning rules. The learning equations used are those of the backpropagation algorithm. In this work, the solution of the kinematics of a six-degrees-of-freedom robot manipulator is implemented by using ANN. Work has been undertaken to find the best ANN configurations for this problem. Both the placement and orientation angles of a robot manipulator are used to fin the inverse kinematics solutions.     

冗余自由度超声检测机器人的逆运动学分析

针对一类冗余自由度超声检测机器人的传统逆运动学求解算法耗时长且准确度低的问题,提出了一种基于集合划分和解析解法相结合的逆运动学求解算法。首先采用De-navit-Hartenberg方法建立检测机器人的运动学方程;其次,利用解析解法求出机器人逆解的解析表达式,并提出三种自由度分配方案;最后,选择合适的自由度分配方案,据此对超声波探头位姿集合作划分,结合逆解解析式求出运动学逆解。实际应用中,借助十一轴超声波检测机器人,利用该算法对具有复杂外形的飞机螺旋桨叶片进行检测。结果表明,与传统的纯数值解法相比,该算法能够快速得到精确的运动学逆解。     

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.