Fuzzy and Recurrent Neural Network Motion Control among Dynamic Obstacles for Robot Manipulators

An integration of fuzzy controller and modified Elman neural networks (NN) approximation-based computed-torque controller is proposed for motion control of autonomous manipulators in dynamic and partially known environments containing moving obstacles. The fuzzy controller is based on artificial potential fields using analytic harmonic functions, a navigation technique common used in robot control. The NN controller can deal with unmodeled bounded disturbances and/or unstructured unmodeled dynamics of the robot arm. The NN weights are tuned on-line, with no off-line learning phase required. The stability of the closed-loop system is guaranteed by the Lyapunov theory. The purpose of the controller, which is designed as a neuro-fuzzy controller, is to generate the commands for the servo-systems of the robot so it may choose its way to its goal autonomously, while reacting in real-time to unexpected events. The proposed scheme has been successfully tested. The controller also demonstrates remarkable performance in adaptation to changes in manipulator dynamics. Sensor-based motion control is an essential feature for dealing with model uncertainties and unexpected obstacles in real-time world systems.     

Robust neuro-fuzzy sensor-based motion control among dynamic obstacles for robot manipulators

A new robust neuro-fuzzy controller for autonomous and intelligent robot manipulators in dynamic and partially known environments containing moving obstacles is presented. The navigation is based on a fuzzy technique for the idea of artificial potential fields (APFs) using analytic harmonic functions. Unlike the fuzzy technique, the development of APFs is computationally intensive. A computationally efficient processing scheme for fuzzy navigation to reasoning about obstacle avoidance using APF is described, namely, the intelligent dynamic motion planning. An integration of a robust controller and a modified Elman neural networks (MENNs) approximation-based computed-torque controller is proposed to deal with unmodeled bounded disturbances and/or unstructured unmodeled dynamics of the robot arm. The MENN weights are tuned online, with no off-line learning phase required. The stability of the overall closed-loop system, composed by the nonlinear robot dynamics and the robust neuro-fuzzy controller, is guaranteed by the Lyapunov theory. The purpose of the robust neuro-fuzzy controller is to generate the commands for the servo-systems of the robot so it may choose its way to its goal autonomously, while reacting in real-time to unexpected events. The proposed scheme has been successfully tested. The controller also demonstrates remarkable performance in adaptation to changes in manipulator dynamics. Sensor-based motion control is an essential feature for dealing with model uncertainties and unexpected obstacles in real-time world systems.     

基于FNN的覆冰机器人越障机械臂轨迹跟踪控制

覆冰机器人除冰时要跨越各种障碍物。采用卡尔曼滤波学习算法,将自适应模糊神经网络控制器用于覆冰机器人越障时的机械臂轨迹跟踪控制,解决了BP算法实时性差的问题。经过仿真实验论证,该方法对覆冰机器人越障时的机械臂轨迹跟踪控制具有很好的效果,表明控制策略和理论分析的可行性。     

Two-stage adaptive robot position/force control using fuzzy reasoning and neural networks

Many studies have been performed on the position/force control of robot manipulators. Since the desired position and force required to realize certain tasks are usually designated in the operational space, the controller should adapt itself to an environment and generate the control force vector in the operational space. On the other hand, the friction of each joint of a robot manipulator is a serious problem since it impedes control accuracy. Therefore, the friction should be effectively compensated for in order to realize precise control of robot manipulators. Recently, soft computing techniques (fuzzy reasoning, neural networks and genetic algorithms) have been playing an important role in the control of robots. Applying the fuzzy-neuro approach (a combination of fuzzy reasoning and neural networks), learning/adaptation ability and human knowledge can be incorporated into a robot controller. In this paper, we propose a two-stage adaptive robot manipulator position/force control method in which the uncertain/unknown dynamic of the environment is compensated for in the task space and the joint friction is effectively compensated for in the joint space using soft computing techniques. The effectiveness of the proposed control method was evaluated by experiments.     

Neural network Reinforcement Learning for visual control of robot manipulators

It is known that most of the key problems in visual servo control of robots are related to the performance analysis of the system considering measurement and modeling errors. In this paper, the development and performance evaluation of a novel intelligent visual servo controller for a robot manipulator using neural network Reinforcement Learning is presented. By implementing machine learning techniques into the vision based control scheme, the robot is enabled to improve its performance online and to adapt to the changing conditions in the environment. Two different temporal difference algorithms (Q-learning and SARSA) coupled with neural networks are developed and tested through different visual control scenarios. A database of representative learning samples is employed so as to speed up the convergence of the neural network and real-time learning of robot behavior. Moreover, the visual servoing task is divided into two steps in order to ensure the visibility of the features: in the first step centering behavior of the robot is conducted using neural network Reinforcement Learning controller, while the second step involves switching control between the traditional Image Based Visual Servoing and the neural network Reinforcement Learning for enabling approaching behavior of the manipulator. The correction in robot motion is achieved with the definition of the areas of interest for the image features independently in both control steps. Various simulations are developed in order to present the robustness of the developed system regarding calibration error, modeling error, and image noise. In addition, a comparison with the traditional Image Based Visual Servoing is presented. Real world experiments on a robot manipulator with the low cost vision system demonstrate the effectiveness of the proposed approach.     

Design and performance of an intelligent predictive controller for a six-degree-of-freedom robot using the Elman network

The aim of this paper was to propose a recurrent neural network-based predictive controller for robotic manipulators. A neural network controller for a six-joint Stanford robotic manipulator was designed using the generalized predictive control (GPC) and the Elman network. The GPC algorithm, which is a class of digital control method, requires long computational time. This is a disadvantage in real-time robot control; therefore, the Elman network controller was designed to reduce processing time by avoiding the highly mathematical and computational complexity of the GPC. The main reason for choosing the Elman network, amongst several neural network algorithms, was that the presence of feedback loops have a profound impact on the learning capability of the network. The designed neural network controller was able to recover quickly because of its significant generalization capability, which allowed it to adapt very rapidly to changes in inputs. The performance of the controller was also shown graphically using simulation software, including the dynamics and kinematics of the robot model.     

机械手臂的多模型预测控制

针对机械手臂的非线性特点,提出了基于隶属度函数的多模型预测控制方法。该方法首先根据机械手臂的特点,选择合适的调度变量,将机械手臂的工作空间划分为若干个工作子空间,在每个子空间内的平衡点处对机械手臂进行线性化处理,得到相应的线性子模型,从而得到机械手臂的多模型表示;其次针对每个线性子模型设计局部预测控制器,使其在相应的子空间内达到控制要求;最后选择梯形隶属度函数与局部预测控制器进行加权求和,获得全局多模型预测控制器,以对机械手臂进行控制。仿真结果表明,当机械手臂的工作条件在大范围内变化时,全局多模型预测控制器的控制性能远优于常规PD控制器,达到了预期的控制目的。     

Neural network controllers for robot manipulators application of damping neurons

^_This paper presents an effective adaptive neural network feedback controller for force control of robot manipulators in an unknown environment by applying damping neurons which possess elastic-viscous properties. The unexpected overshooting and oscillation caused by the unknown and/or unmodeled dynamics of a robot manipulator and an environment can be decreased efficiently by the effect of the proposed damping neurons. Furthermore, a fuzzy controlled evaluation function is applied for the learning of the proposed neural network controller, so that the controller is able to adapt to the unknown environment more effectively. The effectiveness of the proposed neural network controller is evaluated by experiment with a 3 d.o.f. direct-drive planar robot manipulator.     

Methodology of Concept Control Synthesis to Avoid Unmoving and Moving Obstacles (II)

Dynamic path generation problem of robot in environment with other unmoving and moving objects is considered. Generally, the problem is known in literature as find path or robot motion planning. In this paper we apply the behavioral cloning approach to design the robot controller. In behavioral cloning, the system learns from control traces of a human operator. The task for the given problem is to find a controller not only in the form of the explicit mathematical expression. So RBF neural network is used also. The goal is to apply controller for the mobile robot motion planning in situation with infinite number of obstacles. The advantage of this approach lies in the fact that a complete path can be defined off-line, without using sophisticated symbolical models of obstacles.     

A neural framework for adaptive robot control

This paper investigates how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems such as motion control and behavior generation. We have designed an adaptive motion control approach based on a novel recurrent neural network, called Echo state networks. The advantage is that no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters in the robot. To generate the robot behavior over time, we adopted a biologically inspired approach called neural fields. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction, which navigates a mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles.     

Obstacle Modelling Oriented to Safe Motion Planning and Control for Planar Rigid Robot Manipulators

Trajectory planning and tracking are crucial tasks in any application using robot manipulators. These tasks become particularly challenging when obstacles are present in the manipulator workspace. In this paper a n-joint planar robot manipulator is considered and it is assumed that obstacles located in its workspace can be approximated in a conservative way with circles. The goal is to represent the obstacles in the robot configuration space. The representation allows to obtain an efficient and accurate trajectory planning and tracking. A simple but effective path planning strategy is proposed in the paper. Since path planning depends on tracking accuracy, in this paper an adequate tracking accuracy is guaranteed by means of a suitably designed Second Order Sliding Mode Controller (SOSMC). The proposed approach guarantees a collision-free motion of the manipulator in its workspace in spite of the presence of obstacles, as confirmed by experimental results.     

Learning to Recognize and Grasp Objects

We apply techniques of computer vision and neural network learning to get a versatile robot manipulator. All work conducted follows the principle of autonomous learning from visual demonstration. The user must demonstrate the relevant objects, situations, and/or actions, and the robot vision system must learn from those. For approaching and grasping technical objects three principal tasks have to be done—calibrating the camera-robot coordination, detecting the desired object in the images, and choosing a stable grasping pose. These procedures are based on (nonlinear) functions, which are not known a priori and therefore have to be learned. We uniformly approximate the necessary functions by networks of gaussian basis functions (GBF networks). By modifying the number of basis functions and/or the size of the gaussian support the quality of the function approximation changes. The appropriate configuration is learned in the training phase and applied during the operation phase. All experiments are carried out in real world applications using an industrial articulation robot manipulator and the computer vision system KHOROS.     

Intelligent Adaptive Mobile Robot Navigation

This paper deals with the application of a neuro-fuzzy inference system to a mobile robot navigation in an unknown, or partially unknown environment. The final aim of the robot is to reach some pre-defined goal. For this purpose, a sort of a co-operation between three main sub-modules is performed. These sub-modules consist in three elementary robot tasks: following a wall, avoiding an obstacle and running towards the goal. Each module acts as a Sugeno–Takagi fuzzy controller where the inputs are the different sensor information and the output corresponds to the orientation of the robot. The rule-base is generated by the controller after some learning process based on a neural architecture close to that used by Wang and Menger. This leads to adaptive neuro-fuzzy inference systems (ANFIS) (one for each module). The adaptive navigation system (ANFIS), based on integrated reactive-cognitive parts, learns and generates the required knowledge for achieving the desired task. However, the generated rule-base suffers from redundancy and abundance of data, most of which are less useful. This makes the assignment of a linguistic label to the associated variable difficult and sometimes counter-intuitive. Consequently, a simplification phase allowing elimination of redundancy is required. For this purpose, an algorithm based on the class of fuzzy c-means algorithm introduced by Bezdek and we have developed an inclusion structure. Experimental results confirm the meaningfulness of the elaborated methodology when dealing with navigation of a mobile robot in unknown, or partially unknown environment.     

六自由度检修机械臂合理路径规划系统设计

为减少六自由度检修机械臂抓取动作花费的时间,设计一种六自由度检修机械臂合理路径规划系统。此次研究的系统硬件部分主要包含主控制器、伺服电机控制器与通信模块。系统软件部分,计算出机器人与障碍物之间的距离,并计算出所有机器人上点与障碍物之间的距离,采用设置虚拟障碍物的创新型人工势场法进行路径规划,避免传统人工势场法的弊端,以保证机器人与障碍物之间有一定的安全距离,以此完成六自由度检修机械臂合理路径规划。实验结果表明,在有障碍的情况下,此次研究的六自由度检修机械臂合理路径规划系统在2~4 min之内就能够完成抓取动作,并且此次研究的系统控制后的关节曲线较为平稳,证明此次研究的六自由度检修机械臂合理路径规划系统具有较好的控制效果,满足了系统设计需求。     

Adaptive variable structure controller of redundant robots with mobile/fixed obstacles avoidance

In this paper, a variable structure adaptive controller is proposed for redundant robot manipulators constrained by moving obstacles. The main objective of the controller is to force the model states of the robot to track those of a chosen reference model. In addition, the controller is designed directly in Cartesian space and no knowledge on the dynamic model is needed, except its structure. The parameters of the controller are adapted using adaptive laws obtained via Lyapunov stability analysis of the closed loop. The performances of the proposed controller are evaluated using a 3 DOF robot manipulator evolving in a vertical plane constrained by a mobile obstacle. The obtained results show its effectiveness compared to other tested variable structure controllers.     

Learning to Recognize and Grasp Objects

We apply techniques of computer vision and neural network learning to get a versatile robot manipulator. All work conducted follows the principle of autonomous learning from visual demonstration. The user must demonstra te the relevant objects, situations, and/or actions, and the robot vision system must learn from those. For approaching and grasping technical objects three principal tasks have to be done—calibrating the camera-robot coordination, detecting the desired object in the images, and choosing a stable grasping pose. These procedures are based on (nonlinear) functions, which are not known a priori and therefore have to be learned. We uniformly approximate the necessary functions by networks of gaussian basis functions (GBF networks). By modifying the number of basis functions and/or the size of the gaussian support the quality of the function approximation changes. The appropriate configuration is learned in the training phase and applied during the operation phase. All experiments are carried out in real world applications using an industrial articulation robot manipulator and the computer vision system KHOROS.     

基于神经网络的机器人自学习控制器

提出一种神经网络与PID控制相结合的机器人自学习控制器.为加快神经网络的 学习收敛性,研究了有效的优化学习算法.以两关节机器人为对象的仿真表明,该控制器使机 器人跟踪希望轨迹,其系统响应、跟踪精度和鲁棒性优于常规的控制策略.     

受限机器人神经形态的变结构位置/力控制

本文基于Ｊｅａｎ和Ｆｕ（１９９３）建立的受限机器人模型的降型阶形式，利用变结构系统理论，设计了具有未知动态的受限机器人轨道／力追踪控制，提出的学习方法仅仅利用了机器人动态模型的一般结构，不需要其精确信息，计算迅速，易于实现，仿真结果验证了提出的方法的有效性。     

Data-Driven Human-Robot Interaction Without Velocity Measurement Using Off-Policy Reinforcement Learning

In this paper, we present a novel data-driven design method for the human-robot interaction (HRI) system, where a given task is achieved by cooperation between the human and the robot. The presented HRI controller design is a two-level control design approach consisting of a task-oriented performance optimization design and a plant-oriented impedance controller design. The task-oriented design minimizes the human effort and guarantees the perfect task tracking in the outer-loop, while the plant-oriented achieves the desired impedance from the human to the robot manipulator end-effector in the inner-loop. Data-driven reinforcement learning techniques are used for performance optimization in the outer-loop to assign the optimal impedance parameters. In the inner-loop, a velocity-free filter is designed to avoid the requirement of end-effector velocity measurement. On this basis, an adaptive controller is designed to achieve the desired impedance of the robot manipulator in the task space. The simulation and experiment of a robot manipulator are conducted to verify the efficacy of the presented HRI design framework.      

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.