A decentralized control system for cooperative transportation by multiple non-holonomic mobile robots

In this paper, we propose a decentralized control system for transporting a single object by multiple non-holonomic mobile robots. Each agent used in the proposed system has two arms, which can steer around a joint offset from the centre point between two driving wheels. One of these mobile robots acts as a leader, who is assumed to be able to plan and to manipulate the omnidirectional motion of the object by using a resolved velocity control. Other robots, referred to as followers, cooperatively transport the object by keeping a constant relative position with the object using a simple PI control. Different from conventional leader–follower type systems that transport an object by multiple robots in coordination, the present followers can plan an action based on their local coordinate and need no absolute positional information. In addition, as a special case, a system consisting of only two robots is introduced, in which the follower robot not only has an arm length controller to follow the leader but also has a fuzzy controller as an avoidance controller to avoid obstacles or a posture controller to keep a desired posture of the object. Simulation results are given to demonstrate the good performance of the proposed systems.     

Quantification of arm kinesthetic sense using an arm motiongenerator

The human response caused by the motion of an object grasped by a human operator is defined as an arm kinesthetic sense. Due to nonlinearity and ambiguity of human senses, there is no absolute standard for quantification of kinesthetic sense. In this research, a so-called two-dimensional (2-D) arm motion generator is developed to emulate various mechanical impedance, i.e., stiffness or damping, characteristics of a human arm. The words representing arm kinesthetic sense are selected and then the subject's satisfaction levels on these words for given impedance values are measured and processed by the semantic differential method and factor analysis. In addition, in order to reflect the individual differences of each subject in the arm kinesthetic sense, compensation for individual differences based on the neural network technique is proposed. Through this proposed algorithm, the human sensations to arm movements described qualitatively can be converted into engineering data ensuring objectivity, reproducibility, and universality. This database can be used to develop user-friendly products related to arm motion     

Robot arm-wrist coordination. Part 1. Quantitative rating

The robotic capability for controlled motion depends upon the robot's ability to coordinate its arm and wrist in order to accomplish the desired task. The objective of this article is to define formally the arm-wrist coordination and to introduce a quantitative measure for it. We develop a mathematical framework that provides for the analysis of the impact of both the fixed manipulator geometry and the changing robot configuration upon the efficiency of arm-wrist coordination. In the companion paper (Part 2). manipulator design guidelines are then formulated to guarantee task decomposition for any desired robot task. Numerical simulations demonstrate the efficacy of these design guidelines.     

Entrainment-enhanced neural oscillator for rhythmic motion control

We propose a new neural oscillator model to attain rhythmic movements of robotic arms that features enhanced entrainment property. It is known that neural oscillator networks could produce rhythmic commands efficiently and robustly under the changing task environment. However, when a quasi-periodic or non-periodic signal is inputted into the neural oscillator, even the most widely used Matsuoka’s neural oscillator (MNO) may not be entrained to the signal. Therefore, most existing neural oscillator models are only applicable to a particular situation, and if they are coupled to the joints of robotic arms, they may not be capable of achieving human-like rhythmic movement. In this paper, we perform simulations of rotating a crank by a two-link planar arm whose joints are coupled to the proposed entrainment-enhanced neural oscillator (EENO). Specifically, we demonstrate the excellence of EENO and compare it with that of MNO by optimizing their parameters based on simulated annealing (SA). In addition, we show an impressive capability of self-adaptation of EENO that enables the planar arm to make adaptive changes from a circular motion into an elliptical motion. To the authors’ knowledge, this study seems to be the first attempt to enable the oscillator-coupled robotic arm to track a desired trajectory interacting with the environment.     

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.     

Distributed Motion Constraints for Algebraic Connectivity of Robotic Networks

This paper studies connectivity maintenance of robotic networks that communicate at discrete times and move in continuous space. We propose a distributed coordination algorithm that allows the robots to decide whether a desired collective motion breaks connectivity. We build on this procedure to design a second coordination algorithm that allows the robots to modify a desired collective motion to guarantee that connectivity is preserved. These algorithms work under imperfect information caused by delays in communication and the robots’ mobility. Under very outdated information, the proposed algorithms might prevent some or all of the robots from moving. We analyze the correctness of our algorithms by formulating them as games against a hypothetical adversary who chooses system states consistent with observed information. The technical approach combines tools from algebraic graph theory, linear algebra, and nonsmooth analysis.     

面向智能假肢手臂的生机接口系统与类神经协同控制

针对肢体残障患者的假肢控制问题,搭建了一种基于s EMG（表面肌电信号）的智能假肢手臂系统,实现手臂残障程度较高患者的手-肘协调控制。首先,基于肌肉协同理论,使用非负矩阵分解（NMF）方法提取肌肉协同作用,并进行手部动作识别以及肘关节的连续运动估计。其次,基于意图识别结果构建“前馈-反馈”控制框架,对受试者进行前馈监督与反馈检测;根据前馈-反馈结果调整期望的控制输入,提高假肢系统的舒适性与鲁棒性。然后,针对手部动作,构建一种自适应调整抓握力度的框架,通过力、位信息交替控制,实现不同刚度、不同形状物体的自适应抓握;对于肘部运动,设计一种基于识别结果的阻抗控制算法,实现手-肘一体化假肢的稳定的人机交互控制。最后,由6名健康受试者、1名手臂残障受试者对以上控制策略进行实验验证,对手臂整体运动实现了较为准确的意图识别,同时也完成了稳定的肘部屈伸以及手部抓取,做到了手-肘的一体化协调控制。最终该套系统在北京2022年冬残奥会实现了应用展示。     

Practical Point-to-Point Multiple-Goal Task Realization in a Robot Arm with a Rotating Table

This study presents a multiple-goal task realization in a system composed of a 6-d.o.f. robot arm and a one-axis rotating table. The problem is complex due to the existence of multiple goals and the kinematic redundancy of the system. We propose a design approach integrating the base placement, task sequencing and motion coordination methods. We show that this approach reduces the task completion time of the robot arm; the motion planning is realized through straight-line paths in the configuration space despite collision occurrences. Furthermore, we introduce a hybrid graph-search method combining the greedy nearest-neighbor method and the Dijkstra method to solve the motion coordination of the robot arm and the table. We show the effectiveness of the design approach and the search method through a time-constrained simulation-based optimization.     

基于分级规划策略的拟人机械臂仿人运动规划算法研究

为使拟人机械臂具有高精度的仿人运动,提出一种通过触发条件和分级规划策略 的仿人运动新方法。将人臂运动过程离散为不同运动阶段,在每一个运动阶段都有与之对应的 规划层,在不同的规划层中,拟人机械臂的运动特点不同。利用各自的特点建立不同规划层下 的运动模型及臂姿预测指标,对拟人机械臂臂姿进行预测。最后,以NAO 机器人为实验平台, 比较所提方法与最小势能法(MTPE)的静态臂姿与动态臂姿预测,并与运动捕捉系统(OptiTrack) 采集的真实人臂运动数据进行比较。实验表明,该方法具有较小的静态臂姿和动态臂姿预测误 差,能使拟人机械臂产生高度逼真的仿人运动。     

Efficient neural chaotic generator for image encryption

In this paper, we propose a new implementation of chaotic generator using artificial neural network. Neural network can act as an efficient source of perturbation in the chaotic generator which increases the cycleʼs length, and thus avoid the dynamical degradation due to the used finite dimensional space. On the other hand, the use of neural network enlarges the key space of the chaotic generator in an enormous way. The efficiency of the proposed neural chaotic generator is illustrated using some dynamical and NIST statistical tests. We also propose in this paper, a new image encryption method based on chaotic sequence, and the obtained results emphasize the efficiency of our technique.     

变参数PI与神经网络控制的风电系统仿真

建立了交流励磁风力发电机系统的仿真模型.针对交流励磁发电机数学模型的强非线?参数时变性等特点,提出了变参数PI与神经网络的协调控制方法.以交流励磁风力发电机的最佳风能跟踪控制为目的,对基于变参数PI与神经网络协调控制的交流励磁风力发电机控制系统进行了仿真研究.仿真结果表明所提的控制方法具有良好的动、静态性能和较强的鲁棒性,是一种适合在线学习的新型交流励磁风力发电机励磁控制方法.     

Adaptive recurrent neural network control of uncertain constrained nonholonomic mobile manipulators

In this article, motion/force control problem of a class of constrained mobile manipulators with unknown dynamics is considered. The system is subject to both holonomic and nonholonomic constraints. An adaptive recurrent neural network controller is proposed to deal with the unmodelled system dynamics. The proposed control strategy guarantees that the system motion asymptotically converges to the desired manifold while the constraint force remains bounded. In addition, an adaptive method is proposed to identify the contact surface. Simulation studies are carried out to verify the validation of the proposed approach.     

Intelligent control system design for UAV using a recurrent wavelet neural network

This paper aims to propose an efficient control algorithm for the unmanned aerial vehicle (UAV) motion control. An intelligent control system is proposed by using a recurrent wavelet neural network (RWNN). The developed RWNN is used to mimic an ideal controller. Moreover, based on sliding-mode approach, the adaptive tuning laws of RWNN can be derived. Then, the developed RWNN control system is applied to an UAV motion control for achieving desired trajectory tracking. From the simulation results, the control scheme has been shown to achieve favorable control performance for the UAV motion control even it is subjected to control effort deterioration and crosswind disturbance.     

Application of a neural network to the generation of a robot arm trajectory

We propose a neural network model generating a robot arm trajectory. The developed neural network model is based on a recurrent-type neural network (RNN) model calculating the proper arm trajectory based on data acquired by evaluation functions of human operations as the training data. A self-learning function has been added to the RNN model. The proposed method is applied to a 2-DOF robot arm, and laboratory experiments were executed to show the effectiveness of the proposed method. Through experiments, it is verified that the proposed model can reproduce the arm trajectory generated by a human. Further, the trajectory of a robot arm is successfully modified to avoid collisions with obstacles by a self-learning function.This work was presented, in part, at the 9th International Symposium on Artificial Life and Robotics, Oita, Japan, January 28–30, 2004     

Motion/force control scheme for electrically driven cooperative multiple mobile manipulators

This paper presents the motion and force control problem of rigid-link electrically driven cooperative mobile manipulators handling a rigid object. Although, the motion/force control problem of cooperative mobile manipulators has been enthusiastically studied. But there is little research on the motion/force control of electrically driven cooperative mobile manipulators. Due to the inclusion of the actuator dynamics with the manipulator’s dynamics, the controller exhibits some important characteristics. For the electromechanical system, we have designed a novel controller at the dynamic level as well as at the actuator level. In the proposed control scheme, at the dynamic level, uncertain non-linear mechanical dynamics is approximated with a hybrid controller containing model-based control scheme combined with model-free neural network based control scheme together with an adaptive bound. The adaptive bound is used to suppress the effects of external disturbances, friction terms, and reconstruction error of the neural network. At the actuator level, for the approximation of the unknown electrical dynamics, the model-free neural network is utilized. The developed control scheme provides that the position tracking errors, as well as the internal force, converge to the desired levels. Additionally, direct current motors are also controlled in such a way that the desired currents and torques can be attained. In order to make the overall system to be asymptotically stable, online learning of the weights and the parameter adaptation of the parameters is utilized in the Lyapunov function. The superiority of the developed control method is carried out with the numerical simulation results and its superior robustness is shown in a comparative manner.     

Adaptation and learning in control of voluntary movement by the central nervous system

In order to control voluntary movements, the central nervous system must solve the following three computational problems at different levels: (1) the determination of a desired trajectory in visual coordinates; (2) the transformation of its coordinates into body coordinates; and (3) the generation of motor command. Concerning these problems, relevant experimental observations obtained in the field of neuroscience are briefly reviewed. On the basis of physiological information and previous models, we propose computational theories and a neural network model which account for these three problems. (1) A minimum torque-change model which predicts a wide range of trajectories in human multi-joint arm movements is proposed as a computational model for trajectory formation. (2) An iterative learning scheme is presented as an algorithm which solves the coordinate transformation and the control problem simultaneously. This algorithm can be regarded as a Newton-like method in function spaces. (3) A neural network model for generation of motor command is proposed. This model contains internal neural models of the motor system and its inverse system. The inverse-dynamics model is acquired by heterosynaptic plasticity using a feedback motor command (torque) as an error signal. The hierarchical arrangement of these neural networks and their global control are discussed. Their applications to robotics are also discussed.     

Robust Neural Network Motion Tracking Control of Piezoelectric Actuation Systems for Micro/Nanomanipulation

This paper presents a robust neural network motion tracking control methodology for piezoelectric actuation systems employed in micro/nanomanipulation. This control methodology is proposed for tracking of desired motion trajectories in the presence of unknown system parameters, nonlinearities including the hysteresis effect and external disturbances in the control systems. In this paper, the related control issues are investigated, and a control methodology is established including the neural networks and a sliding control scheme. In particular, the radial basis function (RBF) neural networks are chosen for function approximations. The stability of the closed-loop system, as well as the convergence of the position and velocity tracking errors to zero, is assured by the control methodology in the presence of the aforementioned conditions. An offline learning procedure is also proposed for the improvement of the motion tracking performance. Precise tracking results of the proposed control methodology for a desired motion trajectory are demonstrated in the experimental study. With such a motion tracking capability, the proposed control methodology promises the realization of high-performance piezoelectric actuated micro/nanomanipulation systems.      

Myoelectric arm using artificial neural networks to reduce cognitive load of the user

Today’s multiple degree-of-freedom myoelectric prosthesis relies only on direct control by the processed electromyographic signal. However, it is difficult for the wearer to learn unnatural muscle contractions in order to wield more than three DoFs of the arm. This makes it almost impossible to use more complex prostheses with a larger number of actuators. Methods based on sensor–actuator loop and artificial intelligence may reduce cognitive load of the user by removing low level control, and an intelligent control system would make it needless to micromanage every action. For this purpose, sensor system for body segments motion capture was developed, as well as sensor system for prosthetic limb’s environment motion capture. Neural networks were designed to process data from the sensor systems. For the identification of the knee angle, orientation trackers were used. Neural network predictor of arm positions predicts the shoulder angle using the information about movement of the lower limb. In the case of the periodic/cyclic movements of the legs, such as walking, the control unit uses typical movement patterns of the healthy upper limb. Ultrasonic range sensors are used to create 3D map of objects in the environment around the arm. Neural network predictor of object positions predicts collisions. If the potential collisions are identified, the control unit stops arm movement. The new methods were verified by MATLAB and are designed as a part of assistive technology for disabled people and are to be understood as an original contribution to the investigation of new prosthesis control units and international debate on the design of new myoelectric prostheses.

     

Impedance Control with On-Line Neural Network Compensator for Dual-Arm Robots

A controller design strategy of dual-arm robots is proposed in this paper. The controller consists of a central controller and three force controllers. The central controller is used to calculate each arms force command according to the desired object motion. A force controller is used in each arm to track the commanding force. Another force controller is used to track the desired contact force between the manipulated object and its environment. The force controller can be partitioned into three parts. The computed torque method is used to linearize and decouple the dynamics of a manipulator. An impedance controller is then added to regulate the mechanical impedance between the manipulator and its environment. In order to track a reference force signal, an on-line neural network is used to compensate the effect of unknown parameters of the manipulator and environment. The simulation results are reported to show the performance of the neural network compensator.     

时空域融合的骨架动作识别与交互研究

在人体骨架结构动作识别方法中,很多研究工作在提取骨架结构上的空间信息和运动信息后进行融合,没有对具有复杂时空关系的人体动作进行高效表达。本文提出了基于姿态运动时空域融合的图卷积网络模型(PM-STFGCN)。对于在时域上存在大量的干扰信息,定义了一种基于局部姿态运动的时域关注度模块(LPM-TAM),用于抑制时域上的干扰并学习运动姿态的表征。设计了基于姿态运动的时空域融合模块(PM-STF),融合时域运动和空域姿态特征并进行自适应特征增强。通过实验验证,本文提出的方法是有效性的,与其他方法相比,在识别效果上具有很好的竞争力。设计的人体动作交互系统,验证了在实时性和准确率上优于语音交互系统。