Guiding a mobile robot with cellular neural networks

We show how cellular neural networks (CNNs) are capable of providing the necessary signal processing needed for visual navigation of an autonomous mobile robot. In this way, even complex feature detection and object recognition can be obtained in real time by analogue hardware, making fully autonomous real‐time operation feasible. An autonomous robot was first simulated and then implemented by simulating the CNN with a DSP. The robot is capable of navigating in a maze following lines painted on the floor. Images are processed entirely by a CNN‐based algorithm, and navigation is controlled by a fuzzy‐rule‐based algorithm. Copyright © 2002 John Wiley & Sons, Ltd.     

基于Google Glass的远程解放双手式机器人控制系统

随着人机交互技术的发展,解放双手的技术也日益繁荣。在面对复杂任务时,解放双手的技术提供了新的交互渠道,丰富了交互信号的来源。利用Google Glass穿戴式的特点,搭建了一个解放双手的移动机器人远程控制系统。该系统运用互补滤波器融合加速度传感器、陀螺仪以及地磁传感器的测量数据检测操作者的头部运动,并根据设计的控制器解析操作者的控制意图,然后经WiFi传送给被控机器人。同时,运用互补滤波器的高通滤波器成分成功地抑制了头部参考位置的漂移。为了验证系统的灵活性和可靠性,对其进行避障实验测试。实验结果表明,操作者能够流畅地控制机器人完成任务,成功地从任务中解放出双手,为遥控移动机器人提供了新的方式。此外,这一解放双手的系统对双手残疾者也大有益处。     

基于自适应模糊滑模控制的机器人轨迹跟踪算法

针对控制参数的不确定性以及存在未知外部扰动情况下移动机器人的轨迹跟踪问题,提出一种基于光滑非线性饱和函数的自适应模糊滑模轨迹跟踪控制算法。通过建立不确定非线性移动机器人运动控制模型,利用自适应模糊逻辑系统构建自适应模糊滑模控制器。为了增强轨迹跟踪控制算法对随机不确定外部扰动适应能力的同时削弱滑模控制算法中的输入抖振现象,利用有界输入有界输出(BIBO)稳定的方法,通过带有自适应调节算法的模糊系统对滑模控制律中非线性函数项进行自适应逼近,并设计了模糊系统中可调参数的自适应控制律,保证了控制系统的稳定与收敛。实验结果表明,所设计的控制器对系统参数不确定性和外界扰动均具有较强的轨迹跟踪性能和鲁棒性。与传统的滑模控制算法相比,该算法不仅能有效减小输入抖振而且轨迹跟踪控制精度提高了18.89%。     

机器人轮椅用户行为与自主导航动态共享控制方法

机器人轮椅人机交互研究表明长时间采用单一模式交互容易导致用户操作意图误判且稳定性会变差,完全自主模式亦会因用户缺乏控制体验而产生沮丧情绪。针对当前基于人机协作的机器人轮椅交互存在模式间硬切换与缺乏对环境变化的动态调整能力的问题,本文以手势交互控制轮椅为基础,提出一种基于用户行为与自主导航相结合的机器人轮椅动态共享控制方法。首先基于Leap Motion传感器追踪用户掌心坐标,生成用户手势速度指令;其次,基于RPLIDAR A1激光雷达传感器并结合自主导航算法,生成自主导航控制指令;最后基于距离、疲劳及误差等多种约束条件实时更新人-机控制指令权重,实现对机器人轮椅的动态共享控制。实验结果表明,本文所提动态共享控制方法能根据轮椅运行环境与用户操作性能动态调整不同模式间的角色分配,避免了不同模式间的直接硬切换,具有较好的用户体验。     

A framework for adaptive motion control of autonomous sociable guide robot

We present a framework by which the motion of an autonomous mobile guide robot is adaptively controlled. A sociable robot should adapt its speed and path to suit the users' activities, without restricting the user movement. By generating adaptive artificial potential fields for the users and the subgoal separately, and integrating them with the basic potential fields generated from obstacles, our robot can adapt to the users' activities and provide sociable tour‐guide services. The robot predicts a user's moving speed and adapts to it to maintain the social distance. Moreover, with the proposed framework, users can deviate from the guided path temporarily and return to the original task afterward. Instead of waiting for the users and taking the risk of losing them, the robot deviates from its original path to follow the users and also prepares for returning to the guiding task. The robot restarts the guiding task at that place, which ensures the least cost to reach the goal. Simulation and experimental results show that our framework can automatically generate suitable motion patterns to control the robot adaptively, making it sociable while providing tour guide services. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Two-stage optimization algorithm for short-term reactive power planning based on zonal approach

There are various methods for procurement of reactive power as an ancillary service in deregulated market environment. Reactive power market model based on voltage control zones and two-step optimal power flow algorithm is proposed in this paper. Zones are formed by splitting the power system or a control area of an interconnected power system into autonomous voltage sub-areas with sufficient reactive power reserves using the electrical distance method. Every zone formes a single reactive power market. First step of an optimization algorithm determines zonal reactive power prices based on generator's cost functions for reactive power production. Total cost minimization is the goal of the second optimization step where the final dispatching decision is made according to transmission losses and zonal reactive power prices respecting power system planned conditions and security constraints. Proposed algorithm is tested on IEEE 39 bus test system ensuring the system operator's minimal payment for reactive power and transmission losses, without jeopardizing power system security.     

融合行人运动信息的室内移动机器人动态避障方法

为了提高移动机器人在室内人机共融环境下的运动安全和交互性,提出了一种融合行人运动信息的室内移动机器人动 态避障方法,同时考虑任务约束和社会规则。 首先,利用 YOLO v3 算法和 Deep Sort 算法分别对室内环境中的行人进行实时检 测与目标跟踪,计算行人在过去时刻的历史轨迹。 然后,利用 Social-GAN 算法构建行人交互模型,实现轨迹预测。 在此基础上, 将行人的运动状态融合进机器人避障算法之中,根据社会规则设计评价函数,对机器人采样速度样本进行评估,使移动机器人 能够以安全和舒适的方式绕过行人,确保室内人机共融环境下移动机器人的社会接受性。 通过实验对比分析,与传统 DWA 方 法相比,本文方法不仅可以提高机器人导航避障效率,在相同室内场景下导航避障时间由 23. 56 s 提高到 19. 38 s,而且可以有 效降低与行人发生碰撞的风险,保证机器人导航的安全和社交性。     

全方位移动机器人模糊自适应PID控制

针对全方位移动机器人,结合PID和模糊控制两者的优点,提出了一种模糊自适应PID(FAPID)的控制方法。对模糊自适应PID控制算法进行了理论分析,基于Matlab建立了全方位移动机器人的简化仿真模型。仿真研究表明,采用模糊自适应PID控制方法,系统的调节时间缩短,响应速度加快,抗干扰能力和适应参数变化的能力要优于常规的PID控制。     

Adaptive relative velocity estimation algorithm for autonomous mobile robots using the measurements on acceleration and relative distance

In this article, an adaptive algorithm is proposed for online velocity estimation of the autonomous mobile robots (AMRs) without positioning data received from a Global Positioning System (GPS) module or other means for odometry. Unlike the popular Kalman and particle filters that use the measurements on vectors of global (or local) position and acceleration of a mobile robot, the proposed adaptive relative velocity estimation (ARVE) algorithm requires the scalar value of measured distance to a beacon agent and also the measurement on acceleration vector, in order to generate an online estimation of the global velocity vector of a mobile robot. Combining the ARVE algorithm with the recently proposed adaptive relative position estimation (ARPE) algorithm provides a solution for online estimation of the translational states of a mobile robot without accessing the GPS data, which makes the package applicable in both indoor and outdoor environments. The stability of the ARVE algorithm is analyzed with LaSalle-Yoshizawa theorem. In addition, two simulation studies are provided to show the application of the proposed estimation package (ARVE+ARPE) for aerial AMRs in two cases corresponding to the stationary and moving beacon agents. In the simulation results, it is shown that the estimation package can be used in conjunction with the recently proposed adaptive model-free control (AMFC) algorithm to achieve desired tracking objective in autonomous movement of a quadrotor, without requiring the information on the internal dynamics of the robot.     

智能控制在自主式移动机器人中的应用

介绍了以单片机SST89E564RD为智能控制系统核心,在轮式自主移动灭火机器人中的应用,系统应用单片机AT89C1051构成多超声传感器子系统控制电路,由此子系统实现对障碍物的测距及机器人的自主避障行走控制;通过光敏传感器实现机器人对光源的感知和寻找。该智能控制无线通信系统部分采用无线通信芯片PTR2000来实现了上位计算机与下位机移动机器人之间的无线通信。     

A control strategy for leveling load power fluctuations with a successive learning fuzzy-neural network based on prediction of average load power

The effective usage of power facilities can be realized by leveling the fluctuating active power and compensating the reactive power. A fuzzy control strategy of superconducting magnetic energy storage (SMES) has been proposed for this purpose. The control results depend on the values of the scaling factors in fuzzy reasoning. Therefore, to obtain better control results, the scaling factor should be successively adjusted according to the load power fluctuations. In this paper, a control strategy based on autotuning of scaling factors and a fuzzy singleton reasoning method using backpropagation in a neural network is proposed for leveling load fluctuations. The prediction and revision of the teaching signal in terms of the energy of the SMES is proposed. The learning rate and the revision of the teaching signal are discussed. Better leveling of load power fluctuation is shown to be achievable by using fuzzy logic and neural networks. © 1997 Scripta Technica, Inc. Electr Eng Jpn, 120(2): 72–81, 1997     

Soft Decision with Soft Target for Car-like Mobile Vehicle in Dynamic Environment

Online flexible operation of a car-like mobile vehicle with non-holonomic constraints in dynamic environment is still a very challenging problem because the surrounding situations are not qualified in static, knowledge is only partial and the execution is often associated with uncertainty. The difficulty lies in the setting of appropriate moving sub-targets in real-time to obtain a collision-free and low-cost path. In this paper, we present a new approach for the autonomous motion control of mobile vehicle in a narrow area with static and dynamic obstacles. It is based on the selection of sub-target points of vehicle's movement called ‘soft target’ which is a target set defined as all possible and reachable via-points in a navigation space. The soft target is acquired by online learning based on the final target and environment information. Each element of it has its membership value in [0, 1] denoting its evaluation degree. With the acquired soft target, soft decision is made like human's decision process by predictive fuzzy control (PFC) to achieve final target safely and economically. The simulation results show the effectiveness and flexibility of the proposed vehicle motion control method. © 2009 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于轨迹测量与人机映射的六自由度机械臂运动追踪模型

本研究提出了一种基于六自由度机械臂的遥操作人机系统,旨在设计一种不依赖穿戴设备且直观易用的操控方式。该系统使用KinectV1摄像头及UR3机械臂,以Microsoft骨骼识别库作为基本的人体姿态识别方法,通过人体手臂与机械臂关节的映射,实现机械臂实时追踪人体手臂动作的任务。同时,采用非线性模型预测控制(NMPC)算法对机械臂运动控制进行优化,并设定模糊规则来实现NMPC参数的自适应调整。实验结果表明,在NMPC的优化作用下,机械臂在x及z两个平动方向的平均位移误差和3个转动方向的平均旋转误差以及关节角变化量平均误差都有了显著的降低。测试结果也表明,机械臂整体动作跟随效果良好,验证了本文提出的映射规则和运动学模型的准确性,以及模糊NMPC控制器的有效性。     

遗传优化模糊PID融合算法的5自由度机械手控制

由于5自由度机械手具有不同的连接方式,其各关节的控制环不是完全独立,相互存在的耦合使得机械手运动呈现出严重的非线性特征,要得到机械手控制的精确运动轨迹比较困难。采用一种改进的传统PID控制与遗传优化的模糊控制融合的控制算法,通过利用两种控制器的并行控制结构和设置加权调节因子,根据偏差绝对值的大小,动态调整两种控制器的输出强度,两种控制器的融合输出控制5个关节的运动。实验仿真和应用表明该算法能大大提高了机械手运动轨迹的控制精度,能得到平滑的运动轨迹,具有较好的实用价值。     

基于工控机+DSP的移动机器人控制系统设计

提出了一种自主越障移动机器人控制系统,该控制系统采用嵌入式工控机+DSP运动控制卡的控制结构,较好地实现了机器人的实时控制和图像采集。介绍了机器人的机械系统结构,基于嵌入式工控机和DSP运动控制卡的开放式控制系统的硬件组成和软件设计,以及基于无线通讯网络的遥操作技术。通过爬斜坡、爬台阶等越障实验,验证了其良好的自主越障能力和环境适应能力。     

基于模糊遗传神经网络的信息融合故障诊断技术及其应用

在基于广义模糊加权型推理的模糊神经网络基础上,融合非一致性遗传算法,建立了一种模糊遗传神经网络。利用模糊遗传神经网络技术建立信息融合中心,对多传感器数据进行融合处理,通过多源互补信息减小故障诊断系统的不确定性。讨论了模糊遗传神经网络多传感器信息融合方法中数据处理、特征向量维数压缩与关联、归一化处理方法等。同时,对模糊遗传神经的构造以及学习训练等内容,也作了较为详细的讨论。并对模糊遗传神经网络信息融合技术应用于变压器状态的实时监测的应用前景进行了初步探讨。     

Control strategy of leveling load power fluctuations based on fuzzy neural networks by tuning coefficients of learning rate with genetic algorithm

The effective usage of the power facilities can be realized by leveling the fluctuating active power and compensating the reactive power. The fuzzy and fuzzy neural network control strategy of superconducting magnetic energy storages (SMES) was proposed for this purpose. The control results depend on the values of coefficients of learning rate in fuzzy neural networks. Therefore, it is desirable to obtain better control results by tuning the coefficients of learning rate to their optimum values. In this paper, the control strategy based on an autotuning of scaling factors with neural network and tuning of coefficients of learning rate of neural network with genetic algorithm is proposed for leveling load fluctuations. Encoding and decoding of coefficients of learning rate and selection, crossover, and mutation within genetic operations are shown, and crossover rate and mutation rate are discussed. Through these methods, we can achieve a better leveling of load power fluctuation by using fuzzy neural network with genetic algorithm. © 1998 Scripta Technica, Electr Eng Jpn, 125(1): 65–72, 1998     

分层模糊控制在两轮移动式倒立摆中的应用

为解决模糊多变量控制中规则数随系统变量数呈指数增长的问题,针对两轮移动式倒立摆运动的特点,提出了一种分层模糊控制器的设计方法,不仅减少模糊规则数而且使模糊控制逻辑变得清晰明了,其中控制参数采用遗传算法整定。仿真结果证实了该方法的控制效果好,系统跟踪速度快。     

基于遗传算法的模糊神经网络在动态系统辨识中的应用

复杂不规则系统的语言建模构成了许多控制／决策系统的核心问题,模糊逻辑是进行语言建模最有效的方法之一。本文介绍了一种基于模糊逻辑、神经网络和遗传算法的语言建模方法,并给出了新型的混合学习算法,即：首先由自组织算法确定出模糊神经网络的初始隶属度函数;其次由最大匹配因子学习算法完成模糊规则确定;最后提出了一种改进的遗传算法用来优化调节已经获得的隶属度函数。通过具体的仿真实例说明了所提出的建模方法在动态系     

Stock price prediction using neural networks with RasID-GA

In general, neural networks are widely used in pattern recognition, system modeling and prediction, and can model complex nonlinear systems. In the previous work, we proposed a novel training algorithm, Adaptive Random Search with Intensification and Diversification combined with Genetic Algorithm (RasID-GA), for training the multibranch recurrent neural networks recently developed. In this paper, RasID-GA has been applied to predict stock market prices using the multibranch feed forward neural networks. We predicted the next day's closing stock price with several past closing stock prices. We used the stock prices of 20 brands for 720 days in order to evaluate the generalization ability of the proposed method. Copyright © 2009 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.