Learning of a controller for non-recurring fast movements

In this paper a learning method is described which enables a conventional industrial robot to accurately execute the teach-in path in the presence of dynamical effects and high speed. After training the system is capable of generating positional commands that in combination with the standard robot controller lead the robot along the desired trajectory. The mean path deviations are reduced to a factor of 20 for our test configuration. For low speed motion the learned controllers' accuracy is in the range of the resolution of the positional encoders. The learned controller does not depend on specific trajectories. It acts as a general controller that can be used for non-recurring tasks as well as for sensor-based planned paths. For repetitive control tasks accuracy can be even increased. Such improvements are caused by a three level structure estimating a simple process model, optimal a posteriori commands, and a suitable feedforward controller, the latter including neural networks for the representation of nonlinear behaviour. The learning system is demonstrated in experiments with a Manutec R2 industrial robot. After training with only two sample trajectories the learned control system is applied to other totally different paths which are executed with high precision as well.     

非完整移动机器人全局路径跟踪控制

根据制导路径跟踪理论,提出了一种非完整移动机器人全局路径跟踪控制方法.这一方法首先在路径坐标系上计算实际位置与期望位置的误差,利用制导的路径跟踪理论,导出消除该误差所需的姿态角和路径参数更新律,然后据此求解角速度及实际控制.文中还给出了初始路径参考点的计算方法,分析了路径跟踪方向和反转方法.稳定性分析证明该方法没有控制奇异点,受控闭环系统全局一致渐近稳定.最后通过移动机器人典型路径跟踪实验验证了所提出方法的可行性.     

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.     

两种连接形式的拖挂式移动机器人路径跟踪控制

拖挂式移动机器人是一种具有不同连接形式的多车体系统.本文对标准连接和非标准连接的拖挂式机器人,研究了前向和倒车路径的跟踪控制.首先,建立系统的运动学模型并进行运动特性分析;其次,基于Lyapunov方法提出一种与期望路径具有一致运动方向的单体机器人全局路径跟踪控制器;然后将其引入到两种拖挂式机器人的前向跟踪控制中,并分别通过运动学变换和反演控制实现了两种连接形式下的倒车跟踪控制,从而使多节车体始终保持一致的运动方向,避免了不合理位形的出现.仿真结果表明该方法的有效性.     

Path-following for linear systems with unstable zero dynamics

A constructive solution to the path-following problem for MIMO linear systems with unstable zero dynamics is developed. While the original control variable steers the system output along the path, the path parameter θ is used as an additional control to stabilize zero dynamics with a feedback law which is nonlinear due to the path constraint. A sufficient condition for solvability of the path-following problem is given in terms of the geometric properties of the path. When this condition is satisfied, an arbitrary small L₂ norm of path-following error can be achieved, thus avoiding performance limitations of the standard reference tracking problem imposed by unstable zero dynamics.     

A robot self-localization system based on omnidirectional color images

A self-localization system for autonomous mobile robots is presented. This system estimates the robot position in previously learned environments, using data provided solely by an omnidirectional visual perception subsystem composed of a camera and of a special conical reflecting surface. It performs an optical pre-processing of the environment, allowing a compact representation of the collected data. These data are then fed to a learning subsystem that associates the perceived image to an estimate of the actual robot position. Both neural networks and statistical methods have been tested and compared as learning subsystems. The system has been implemented and tested and results are presented.     

Criteria for robot performance in path-following activities

Commercial robotic systems often include ambiguous information in their specifications for path-following capabilities and regarding the feasibility of improving path-following through adaptive control. It is necessary to establish criteria to differentiate between the various levels of path following. This paper presents a set of motion criteria and demonstrates how to construct a check scheme according to these criteria. The proposed check scheme provides a powerful tool for assessing robot motion performance and comparing the performance of different systems.     

Microcomputer-based optical sensor for seam tracking robot

One of the present application of robots in industry is for continous motion along a seam path. The purpose of this paper is to illustrate a microprocessor-based optical sensor for an input or feedback device to guide the robot along a complex 3-dimentional path. A linear array detector was used for fast detection of the seam, and several microprocessors are used to control the robot. The elements of the developed system with performance evaluation data obtained, are presented in this paper.     

Developing a mobile robot for transport applications in the hospital domain

We have been developing MKR (Muratec Keio Robot), an autonomous omni-directional mobile transfer robot system for hospital applications. This robot has a wagon truck to transfer luggage, important specimens, and other materials. This study proposes an obstacle collision avoidance technique for the wagon truck pulling robot which uses an omni-directional wheel system as a safe movement technology. Moreover, this paper proposes a method to reach the goal along a global path computed by path planning without colliding with static and dynamic obstacles. The method is based on virtual potential fields. Several modules with different prediction times are processed in parallel to change the robot response according to its relative velocity and position with respect to the obstacles. The virtual force calculated from each potential field is used to generate the velocity command. Some experiments were carried out to verify the performance of the proposed method. From the experimental results in a hospital it was confirmed that the robot can move along its global path, and reach the goal without colliding with static and moving obstacles.     

离轴式拖车移动机器人的任意路径跟踪控制

离轴式拖车移动机器人属于非完整系统,当车头线速度随时间变化且过零变号时,难以用一个控制器实现系统对期望路径的跟踪.本文研究离轴式拖车移动机器人系统的任意路径跟踪问题.首先由系统和虚拟小车的运动学方程得到误差状态模型,线性化后用坐标变换将其化为标准型,然后基于Lyapunov方法构造出一种跟踪控制律.只要车头的运动线速度有界且不趋于零,其导数有界,则所设计的控制律就可以保证系统跟踪任意的期望路径,且跟踪误差最终一致有界,最终界的大小与期望路径的曲率变化率成比例.当期望路径的曲率变化率为零或趋于零时,所设计的控制律可以保证拖车移动机器人指数收敛到期望路径.仿真结果证实了控制律的有效性.     

Adaptive neural control for cooperative path following of marine surface vehicles: state and output feedback

This paper addresses the cooperative path-following problem of multiple marine surface vehicles subject to dynamical uncertainties and ocean disturbances induced by unknown wind, wave and ocean current. The control design falls neatly into two parts. One is to steer individual marine surface vehicle to track a predefined path and the other is to synchronise the along-path speed and path variables under the constraints of an underlying communication network. Within these two formulations, a robust adaptive path-following controller is first designed for individual vehicles based on backstepping and neural network techniques. Then, a decentralised synchronisation control law is derived by means of consensus on along-path speed and path variables based on graph theory. The distinct feature of this design lies in that synchronised path following can be reached for any undirected connected communication graphs without accurate knowledge of the model. This result is further extended to the output feedback case, where an observer-based cooperative path-following controller is developed without measuring the velocity of each vehicle. For both designs, rigorous theoretical analysis demonstrate that all signals in the closed-loop system are semi-global uniformly ultimately bounded. Simulation results validate the performance and robustness improvement of the proposed strategy.     

The study of path error for an omnidirectional home care mobile robot

The first objective of this research was to develop an omnidirectional home care mobile robot. A PC-based controller controls the mobile robot platform. This service mobile robot is equipped with an “indoor positioning system” and an obstacle avoidance system. The indoor positioning system is used for rapid and precise positioning and guidance of the mobile robot. The obstacle avoidance system can detect static and dynamic obstacles. In order to understand the stability of a three-wheeled omnidirectional mobile robot, we carried out some experiments to measure the rectangular and circular path errors of the proposed mobile robot in this research. From the experimental results, we found that the path error was smaller with the guidance of the localization system. The mobile robot can also return to its starting point. The localization system can successfully maintain the robot’s heading angle along a circular path.     

Control Effort Reduction in Tracking Feedback Laws

We develop a path-following algorithm for redesign of tracking feedback laws to reduce the control effort. Our algorithm provides a tradeoff between the control effort and the dynamic performance along the path, while maintaining the desired convergence to the path. We illustrate it on a realistic hovercraft model, and compare the resulting control effort with control efforts of other path-following and tracking algorithms     

双轮驱动移动机器人的学习控制器设计方法*

提出一种基于增强学习的双轮驱动移动机器人路径跟随控制方法,通过将机器人运动控制器的优化设计问题建模为Markov决策过程,采用基于核的最小二乘策略迭代算法(KLSPI)实现控制器参数的自学习优化。与传统表格型和基于神经网络的增强学习方法不同,KLSPI算法在策略评价中应用核方法进行特征选择和值函数逼近,从而提高了泛化性能和学习效率。仿真结果表明,该方法通过较少次数的迭代就可以获得优化的路径跟随控制策略,有利于在实际应用中的推广。     

Use of neural networks in iterative learning control systems

This paper presents an approach to the use of neural networks to improve iterative learning control performance. The neural networks are used to estimate the learning gain of an iterative learning law and to store the learned control input profiles for different reference trajectories. A neural network of piecewise linear approximation is presented to identify effectively the system dynamics, and the approximation property and persistently exciting condition are discussed. In addition, training of a feedforward neural controller is presented to accumulate control information learned by an iterative update law for various reference trajectories. Then, an iterative learning law with a feedforward neural controller is suggested and its convergence property is stated with the convergence condition. The effectiveness of the present methods has been demonstrated through simulations by applying them to a two-link robot manipulator.     

Dynamical neural networks for planning and low-level robot control

We use dynamical neural networks based on the neural field formalism for the control of a mobile robot. The robot navigates in an open environment and is able to plan a path for reaching a particular goal. We will describe how this dynamical approach may be used by a high level system (planning) for controlling a low level behavior (speed of the robot). We give also results about the control of the orientation of a camera and a robot body.     

基于自适应和神经动力学的轮式移动机器人路径跟踪控制(英文)

本文提出一种自适应和神经动力学相结合的轮式移动机器人路径跟踪控制方法.首先,设计运动学控制器用来获得机器人期望速度;其次,考虑机器人动力学模型参数的不确定性,利用模型参考自适应方法来设计动力学控制规律,使得机器人实际速度渐近逼近期望值;再次,为克服速度和力矩的跳变,加入神经动力学模型对控制器进行优化,并且通过Lypunov理论来证明整个控制系统的稳定性;最后仿真结果表明该控制方法的有效性.     

Path-following control of a mobile robot in the presence of actuator constraints

In this paper, we present a control law for a non-holonomic mobile robot that achieves path following. In the path-following problem, the objective is to control the angular velocity of the robot so that the robot tracks a given reference trajectory. In this paper, we propose a control law that achieves path following in the presence of a constraint on the angular velocity. By applying the proposed control law, the robot can track the reference trajectory even if the distance from the initial position of the robot and the reference trajectory is arbitrary large. Further, we extend the control law so that the linear velocity of the robot becomes small when the robot passes through corners. By using the control algorithm, we can prevent the angular velocity of the robot becoming extremely large when the robot passes through corners. Numerical examples are provided to illustrate the effectiveness of the proposed methods.     

基于路径跟踪控制方法的拖挂式机器人系统路径规划算法

为解决拖挂式移动机器人系统路径规划算法精准性低、稳定性差和无法考虑系统间安全性等的问题,提出一种基于路径跟踪方法的路径规划算法。该算法融合快速拓展随机树（RRT）基本算法和路径跟踪控制方程,通过自动拟合样条曲线,跟踪并生成节点间轨迹,以此提高路径精准性;加入系统夹角约束条件和节点击中机制提高算法稳定性和结果安全性;此外,加入贪心优化算法,针对结果路径进行优化处理。通过仿真实验结果表明,相较基本RRT算法,改进算法搜索得到的路径更贴近实际运动轨迹,在安全性和成功率上优于原算法,能够满足快速设计或实时系统的需求。     

Specifying and optimizing robotic motion for visual quality inspection

Installation or even just modification of robot-supported production and quality inspection is a tedious process that usually requires full-time human expert engagement. The resulting parameters, e.g. robot velocities specified by an expert, are often subjective and produce suboptimal results. In this paper, we propose a new approach for specifying visual inspection trajectories based on CAD models of workpieces to be inspected. The expert involvement is required only to select – in a CAD system – the desired points on the inspection path along which the robot should move the camera. The rest of the approach is fully automatic. From the selected path data, the system computes temporal parametrization of the path, which ensures smoothness of the resulting robot trajectory for visual inspection. We then apply a new learning method for the optimization of robot speed along the specified path. The proposed approach combines iterative learning control and reinforcement learning. It takes a numerical estimate of image quality as input and produces the fastest possible motion that does not result in the degradation of image quality as output. In our experiments, the algorithm achieved up to 53% cycle time reduction from an initial, manually specified motion, without degrading the image quality. We show experimentally that the proposed algorithm achieves better results compared to some other policy learning approaches. The described approach is general and can be used with different types of learning and feedback signals.