基于降阶位置/力模型的机器人神经网络控制

双足机器人的双脚支撑期是实现其步行运动的重要过程,然而耦合的位置/力控制难以保证其稳定平滑运动.本文提出了一种基于降阶位置/力模型的机器人控制策略,整合了位置控制子空间模型和力控制子空间模型,通过模型降阶减小了控制器设计的复杂度,并采用神经网络自适应控制方法综合多控制目标,实现了双足机器人的平滑稳定控制并有效地抑制了系统外扰和参数不确定性的影响.最后,仿真算法验证了该控制方法和模型的有效性.     

基于遗传算法的双臂机器人模糊力/位混合控制

近年来,适用于空间站操作的冗余度双臂机器人系统技术研究得到了较多的重视．结合已有的 研究基础和研究条件,本文开展了面向空间舱内作业的冗余度双臂机器人协调控制应用研究．针对双臂机器 人协调操作过程中的受力问题,提出了一种基于遗传算法的双臂机器人模糊力/位混合控制策略．该方法把机 器人末端的力误差通过模糊控制转变为机器人位置控制器的修正值,在不改变机器人原有位置控制器的前提 下,实现力/位混合控制．利用遗传算法离线优化模糊控制规则,为了提高遗传算法的性能,总体交叉概率和 变异概率都采用了自适应控制策略．最后,以冗余度双臂机器人合力协调搬箱为例,进行了力跟踪的三维仿 真和实验,验证了所提出控制策略的有效性和可靠性．     

附加力外环的机器人力／位置自适应模糊控制

提出一种由神经网络训练模糊控制规则的自适应模糊控制器,并应用附加力外环的机器人力／位置控制。在不改变一般工业机器人原有位置控制的前提下,实现力／位置自适应模糊控制。实验结果表明,该方法可使机器人控制系统对工作环境接触刚度的自适应能力得到显著改善。     

自适应模糊与CMAC并行的机器人力/位置控制

为提高机器人系统对机器人末端操纵器与外界工作环境接触时，其接触刚度不确定性的自适应能力，在机器人力／位置混合控制的基础上，设计出了一种基于自适应模糊与CMAC并行控制的机器人力控制器，采用小脑模型神经控制器实现前馈控制，实现被控对象的逆动态模型，自适应模糊控制器实现反馈控制，保证系统的稳定性，且抑制扰动。以平面两关节机器人进行仿真，仿真结果表明，系统的自适应能力和力跟踪能力有显著的提高，机械手在其末端操纵器与刚性变化范围较大的外界工作环境接触时，具有较强的适应能力，较好地完成了机器人的力／位置控制。     

机器人手臂力控制系统GRAFC

本文介绍了一机器人手臂力控制系统及在其上实现的部分力控制作业.此系统以 PUMA 760机器人为本体,以 NKRC-4机器人控制器为基础,采用两级控制结构:上层负责规划、监控,完成力传感信息、视觉信息的采集和处理,接收来自底层的位置反馈信息,并根据一定的控制算法产生控制命令下送给底层;底层完成伺服控制.该系统具有通用性和较强的可靠性。适于各种控制方案和算法的实现.在此系统上我们成功地进行了定力控制、未知表面的跟踪与恢复、精密轴孔装配等作业,验证了系统的性能.     

移动机器人编队的递归模糊神经网络滑模控制

研究非完整移动机器人编队控制优化问题,由于动态模型存在诸多不稳定性,针对领航者-跟随者l-ψ控制结构,提出了一种Back stepping运动学控制器与自适应神经滑模控制器相结合的新型控制策略.采用动态递归模糊神经网络(dynam-ic recurrent fuzzy neural network,DRFNN)对跟随者及领航者动力学非线性不确定部分进行在线估计,并通过自适应鲁棒控制器对神经网络建模误差进行补偿.所提方法不但解决了移动机器人编队控制的参数与非参数不确定性问题,同时也确保了机器人编队在期望队形下对指定轨迹的跟踪;根据Lyapunov方法的设计过程,保证了控制系统的稳定;仿真结果表明了改进方法对机器人编队优化控制的有效性.     

受限柔性机器人臂的鲁棒变结构混合位置/力控制

针对一类平面双连杆受限柔性机器人臂提出一种混合位置/力控制方案,采用鲁棒变 结构控制策略对控制方案进行修正,以改善该柔性机器人系统的鲁棒性,控制机器人终端执行 器的位置和接触力.通过引入变结构鲁棒控制器,可确保输出跟踪误差在有限时间内收敛到零, 或一致终结有界.计算机仿真结果证明了这种控制方案的可行性和有效性.     

受限柔性机器人基于遗传算法的自适应模糊控制

研究一类平面双连杆受限柔性机器人的混合位置/力控制问题,提出一种自适应 模糊逻辑控制方案,利用遗传学习算法对控制器中的参数进行学习和修正,达到提高系统控 制精度、改善系统鲁棒性的目的.计算机仿真结果表明这种控制器设计方案具有很好的特性.     

基于单神经元控制器的独轮自平衡机器人双闭环自适应控制

针对竖直飞轮的独轮自平衡机器人系统,提出了一种基于自适应单神经元控制的双闭环(DLSN)控制方法.根据对独轮自平衡机器人动力学模型的分析,将独轮自平衡机器人分成两个子系统,提出了一种具有俯仰倾角和横滚倾角内环、前向位移外环的双闭环自适应控制结构,其中每个控制环均由单神经元自适应控制器构成.仿真实验结果表明:所设计的基于双闭环单神经元自适应独轮自控制方法是有效的.     

开放式机器人控制器综述

本文对开放式机器人控制器的研究进行了概括和总结,综合叙述了开放式机器人控制 器的思想及优点,从控制结构、硬件和软件实现的角度总结了已有的研究工作,指出了开放 式机器人控制器的发展方向．     

Adaptive force and position control of manipulators

The article presents simple methods for the design of adaptive force and position controllers for robot manipulators within the hybrid control architecture. The force controller is composed of an adaptive PID feedback controller, an auxiliary signal, and a force feedforward term, and achieves tracking of desired force setpoints in the constraint directions. The position controller consists of adaptive feedback and feedforward controllers as well as an auxiliary signal, and accomplishes tracking of desired position trajectories in the free directions. The controllers are capable of compensating for dynamic cross-couplings that exist between the position and force control loops in the hybrid control architecture. The adaptive controllers do not require knowledge of the complex dynamic model or parameter values of the manipulator or the environment. The proposed control schemes are computationally fast and suitable for implementation in online control with high sampling rates. The methods are applied to a two-link manipulator for simultaneous force and position control. Simulation results confirm that the adaptive controllers perform remarkably well under different conditions.     

失重环境下可控柔性臂的模态特性

在非重力场中,考虑控制器动态反馈的影响,对存在控制器定位约束的柔性臂系统进行动力分析,研 究其在相对平衡位置的模态特性．以具有柔性关节和弹性臂杆的可控柔性臂为研究对象,分析了控制器作用下的反 馈约束特性,将控制器位置和速度增益引入力边界条件,得到了耦合控制器参量的模态特征方程,证明了反馈约束 的存在使得系统特征频率为复频率,且模态主振型是复变函数．通过数值仿真,明确了可控柔性臂的模态特性与控 制器增益之间的关系,得到了不同于经典振动理论的结论．设计了可控柔性臂的仿失重实验平台,试验模态结果证 明了理论分析的有效性．     

基于距离传感器的双边遥操作

为了改善双边遥操作的力反馈性能,本文根据从端操作臂上的传感器检测的目标距离信息,设计了新 的PD 双边控制器．证明了系统的稳定性条件,并通过单自由度双边遥操作实验系统,对提出的控制方法进行了实 验验证．实验结果表明,当从端操作臂靠近目标时,主端操作臂产生了逐渐增大的反馈力．这种控制策略为操作者 安全实现遥操作任务提供了有效手段．     

Neural Network Force Control for Industrial Robots

In this paper, we present a hierarchical force control framework consisting of a high level control system based on neural network and the existing motion control system of a manipulator in the low level. Inputs of the neural network are the contact force error and estimated stiffness of the contacted environment. The output of the neural network is the position command for the position controller of industrial robots. A MITSUBISHI MELFA RV-M1 industrial robot equipped with a BL Force/Torque sensor is utilized for implementing the hierarchical neural network force control system. Successful experiments for various contact motions are carried out. Additionally, the proposed neural network force controller together with the master/slave control method are used in dual-industrial robot systems. Successful experiments are carried out for the dual-robot system handling an object.     

面向位控机器人的力/位混合控制

本文提出了一种面向位控机器人的力/位混合控制策略．通过力反馈信息对未知约 束进行估计获得位控和力控方向,根据位控和力控方向对机器人终端的运动轨迹进行规划, 并采用阻抗力控制规律以使机器人获得较好的柔顺性．仿真试验表明,该策略具有较高的力 控制精度和表面跟踪能力．     

On the Robust Nonlinear Motion Position and Force Control of Flexible Joints Robot Manipulators

The design of a robust nonlinear position and force controller for a flexible joints robot manipulator interacting with a rigid environment is presented. The controller is designed using the concept of feedback linearization, sliding mode techniques, and LQE estimation methodologies. It is shown that the nonlinear robot manipulator model is feedback linearizable. A robust performance of the proposed control approach is achieved by accounting for the system parameters uncertainties in the derivation of the nonlinear control law. An upper bound of the error introduced by parametric uncertainties in the system is computed. Then, the feedback linearizing control law is modified by adding a switching action to compensate the errors and to guarantee the achievement of the desired tracking performance. The relationship between the minimum achievable boundary layer thickness and the parametric uncertainties is derived. The proposed controller is tested using an experimental flexible joints robot manipulator, and the results demonstrate its potential benefits in reducing the number of sensors required and the complexity of the design. This is achieved by eliminating the need for nonlinear observers. A robust performance is obtained with minimum control effort by taking into account the effect of system parameter uncertainties and measurement noise.     

A Review of: “Fuzzy Sets and Their Applications”. By C. V. NEGOIT[Abreve] and D. A. RALESCU. (In Rumanian) (Bucharest: Editura Technica, 1974.) [Pp.219.]

This paper presents a new controller for position and force control of robotic devices interacting with passive environments. In this approach, for the manipulator dynamics in joint space, suitable output equations are defined which represent the position control and force control subspaces. The dynamics of the manipulator are projected along these subspaces to obtain the dynamics in the respective subspaces. The resulting dynamics are linearized and decoupled using a nonlinear input-state linearizing controller. For the position control subspace dynamics, desirable stability features are achieved through pole placement design. Along the force control subspace, a soft base is introduced, the compliance effect of which is controlled by an appropriate compensation term. Based on the force feedback information, this compensation is modifed online using an extended dynamics. Assuming a model of the passive environment, aspects of local stability of the controller have been discussed. The theory has been presented for a two-link planar manipulator example, based on which, a numerical simulation is discussed.     

Fuzzy-neuro position/force control for robotic manipulators with uncertainties

The performance of a controller for robot force tracking is affected by the uncertainties in both the robot dynamic model and the environmental stiffness. This paper aims to improve the controller’s robustness by applying the neural network to compensate for the uncertainties of the robot model at the input trajectory level rather than at the joint torque level. A self-adaptive fuzzy controller is introduced for robotic manipulator position/force control. Simulation results based on a two-degrees of freedom robot show that highly robust position/force tracking can be achieved, despite the existence of large uncertainties in the robot model.     

A trivial and efficient learning method for motion and force control

The feedback produced by the linear controller of a manipulator executing a trajectory corresponds approximately to the inverse dynamics necessary to drive this trajectory. When a single movement is repeated, the feedback measured in one run can therefore be used as feedforward for the next runs. The learning position–force controller introduced in this paper is based on this idea and a parallel control of force and position. Experiments on 2- and 3-degree-of-freedom parallel manipulators show the simplicity of its implementation and its efficiency for gradually improving trajectory control in repeated movements. The control is robust to high level of noise and the performance is superior than with a parametric controller based on the rigid-body dynamic model. Simulations suggest that these properties also hold when the force is controlled simultaneously to the position.     

基于Matlab机械臂力控系统仿真研究

以位置控制为主的机械臂控制方法已不能满足某些复杂环境（装配、抛光、去毛刺）的应用要求,控制机械臂与环境间的接触力已成为机器人学研究的一个热点。提出一种在Matlab/SimMechanics环境下平面二自由度机械臂力控制的仿真研究方法。在平面中模拟机械臂与环境的接触面,设计振荡抑制控制器,实现机械臂与环境间接触力的控制,以及机械臂与刚性环境碰撞接触过程中冲击振荡阶段的振荡抑制,生成机械臂期望的运动轨迹。仿真结果表明,该方法可实现特定作业下机械臂与环境间接触力的控制。