基于深度神经网络的多指灵巧手抓取手势优化

基于深度神经网络模型,提出了一种适用于多指灵巧手的抓取手势优化方法。首先,在仿真环境下构建了一个抓取数据集,并在此基础上训练了一个卷积神经网络,依据目标物体单目视觉信息和多指灵巧手抓取位形来预测抓取质量函数,由此可以将多指灵巧手的抓取规划问题转化为使抓取质量最大化的优化问题,进一步,基于深度神经网络中的反向传播和梯度上升算法实现多指灵巧手抓取手势的迭代与优化。在仿真环境中,比较该网络和仿真平台对同一抓取位形的抓取质量评估结果,再利用所提出的优化方法对随机搜索到的初始手势进行优化,比较优化前后手势的力封闭指标。最后,在实际机器人平台上验证本文方法的优化效果,结果表明,本文方法对未知物体的抓取成功率在80%以上,对于失败的抓取,优化后成功的比例达到90%。     

面向水下抓取作业的复合腔体仿生软体手设计

水下机械手在水生物采样、考古打捞等水下作业中起着关键作用,而现有水下机械手存在耦合安全性差、适应性弱及抓取不稳定等问题,使得作业效果并不理想。针对以上问题,本文开展了新型水下软体手的设计与研究。首先提出了具有密封管结构的复合腔体仿生软体驱动器,基于该驱动器设计出一种三指包络型水下软体手;硅胶材料的弹性和流体的可压缩性能够保证目标物的无损抓取,密封管结构可提高深水高压适应能力,保持腔和弯曲腔的复合结构及指纹、指甲的仿生结构提升了软体手耦合适应能力。利用基于Yeoh模型的有限元分析方法及注塑、3D打印等加工技术对软体手进行了结构优化和制作。设计了一套具有较高精度的水压驱动系统来提高软体手耦合稳定性。最后,针对影响机械手水下作业能力的重要因素,模拟相应实验场景对软体手进行了实验测试,实验结果显示软体手纵向抓取力达到26 N,驱动深度可达3000 m,较现有水下软体手均有较大提升;水下目标物抓取测试及与传统水下刚性手的对比实验证明了所提出软体手具有稳定的抓取性能和更好的适应性及安全性,适用于水下目标物的无损抓取作业。     

机器人多指操作的递阶控制

为机器人多指协调操作建立一递阶控制系统.给定一操作任务,任务规划器首先生 成一系列物体的运动速度;然后,协调运动规划器根据期望的物体运动速度生成期望的手指 运动速度和期望的抓取姿态变化;同时,抓取力规划器为平衡作用在物体上的外力,根据当前 的抓取姿态,生成各手指所需的抓取力;最后,系统将手指的期望运动速度与为实现期望抓取 力而生成的顺应速度合并,并通过手指的逆雅可比转化为手指关节运动速度后,由手指的关 节级运动控制器实现手指的运动和抓取力的控制.该控制方法已成功应用于香港科技大学 (HKUST)灵巧手控制系统的开发.实验证明该方法不仅能完成物体轨迹的跟踪控制任务, 而且能完成物体对环境的力控制和力与速度的混合控制.     

多指机器人手协调控制研究进展

本文综述了关于多指机器人手协调控制方面的研究进展情况．文章分为三个部分．第 一部分介绍了多指机器人手各方面的研究现状;第二部分讨论协调控制,主要是力分配算法 方面的研究成果;第三部分探讨了自主抓取的实现方法,并提出对未来研究的设想．     

臂-手系统主动抓取策略及仿真

本文将多指手和关节型机械手臂结合起来，应用多种传感器，组成了仿真人臂－手系统，对多种抓取模式进行了分析，提出了主动抓取目标物体的策略，即将孩童抓取和知识抓取结合起来，由推理机获得抓取模式及算法，最后，对抓取过程进行了图形仿真。     

基于仿人机械手的五指力封闭抓取算法

手是人类在长期进化过程中形成的最完美的工具,能够灵活、精细的进行抓取物体等操作。机械手设计初衷是取代人手完成工作,是机器人系统的重要组成部分,因此抓取物体等操作一直是仿人机械手的研究重点。传统的抓取方法是利用机械手三指形成力封闭完成任务。但由于机械手本身结构复杂等原因,易出现控制信号偏差或某自由度未达到要求水平,使得抓取过程中目标物体脱落等问题。为了使机械手达到稳定抓取的效果,本文提出了一种效仿人手抓取的五指力封闭抓取算法,其本质是利用冗余机制解决传统三指抓取过程中可能出现的抓取不平稳或脱落的问题。首先,基于三指力平衡算法的思想上提出了满足五指力封闭抓取算法的条件。然后,对五指力封闭抓取算法进行了充分性和必要性的证明。最后,通过仿真环境下的实验抓取不同目标物体,验证了五指力封闭算法的可行性及必要性。     

智能化水下机械手的研究

水下机械手的研究和设计对水下机器人的应用和发展具有重要的影响,而智能化水下机械手要具有自主路径规划和目标类型判断的功能.文中首先简要叙述了水下机械手的发展现状和存在问题,然后通过分析抓取任务及环境信息的获取,设计了系统的硬件结构和软件组成.接着通过对水下机械手进行数学建模,阐述了抓取操作的工作原理,并给出了一个抓取过程的实例曲线.     

机器人多指手抓取中的规划问题

在机器人抓取系统中，一般认为需要４种规划器：即策略规划器，触觉规划器，轨迹规划抓取规划器，抓取规划器对成功抓取来说是非常重要的，在抓取规划器中，视觉模块用来把图象变换成物体的描述，接着用抓取模式选择模块把物体的描述换成一系列的控制信号，本文从最优抓取规划和基于专家系统的抓取规划这两个方面，着重从基于专家系统的抓取规划方面对当前机器人多指手抓取规划的研究现状及主要问题进行了深入地剖析。     

基于神经网络的水下机器人力控策略研究

水下机器人抓取物体时,物体与指尖存在力控制问题,但是由于动力学模型、被抓取物体位置和刚度的不确定性,采用传统阻抗控制方法不具有鲁棒性,因此对基于位置的神经网络阻抗控制方法进行了研究,构建了基于位置的神经网络阻抗控制器,采用三层前向反馈神经网络构建补偿器结构,基于BP算法和Delta学习规则,得到了反向传播的更新规则;该神经网络控制系统具有很强的自适应性,可以很好地完成机器手抓取物体的任务;在水下机器人单手指上分别对软性材料(泡沫)和硬性材料(木块)施加5N恒定力进行反复的实验,结果表明,该方法具有较好的补偿和控制效果,为水下机器人的准确抓握和合理操作奠定基础。     

基于多重几何约束的未知物体抓取位姿估计

针对机器人在非结构化环境下面临的未知物体难以快速稳定抓取的问题,提出一种基于多重几何约束的未知物体抓取位姿估计方法.通过深度相机获取场景的几何点云信息,对点云进行预处理得到目标物体,利用简化的夹持器几何形状约束生成抓取位姿样本.然后,利用简化的力封闭约束对样本进行快速粗筛选.对抓取位姿的抓取几何轮廓进行力平衡约束分析,将稳定的位姿传送至机器人执行抓取.采用深度相机与6自由度机械臂组成实验平台,对不同姿态形状的物体进行抓取实验.实验结果表明,本文方法能够有效应对物体种类繁多、缺乏3维模型的情况,在单目标和多目标场景均具有良好的适用性.     

Coordination and Control of Multi-fingered Robot Hands with Rolling and Sliding Contacts

In this paper, the problem of controlling multi-fingered robot hands with rolling and sliding contacts is addressed. Several issues are explored. These issues involve the kinematic analysis and modeling, the dynamic analysis and control, and the coordination of a multi-fingered robot hand system. Based on a hand-object system in which the contacts are allowed to both roll and slide, a kinematic model is derived and analyzed. Also, the dynamic model of the hand-object system with relative motion contacts is studied. A control law is proposed to guarantee the asymptotic tracking of the object trajectory together with the desired rolling and/or sliding motions along the surface of the object. A planning approach is then introduced to minimize the contact forces so that the desired motion of the object and the relative motions between the fingers and the object can be achieved. Simulation results which support the theoretical development are presented.     

A guideline for specifying compliance in multi-fingered operations

In this paper, we present a fundamental compliance analysis for multi-fingered hands and also provide a guideline for specifying compliance characteristics in the three-dimensional operational space of multi-fingered hands. Through the analysis of the stiffness relation between the operational space and the fingertip space of multi-fingered hands, it is shown that some of the coupling stiffness elements cannot be planned arbitrarily. Also, an independent finger-based compliance control method to achieve the given compliance characteristics is described. Conclusively, when we specify the operational stiffness matrix, the contents of the operational stiffness matrix cannot be fully achieved by influence of the grasp geometry of multi-fingered hands. The grasp positions of fingers as well as the RCC point, which are shown important factors, should be chosen to achieve the specified operational stiffness matrix for the given task. The cases of a point contact with friction and soft contact are examined as illustrative examples. It is observed that a five-fingered robotic hand is sufficient for implementation of proper three-dimensional compliance characteristics. © 2004 Wiley Periodicals, Inc.     

Intelligent control of multi-fingered hands

This paper is concerned with intelligent control for grasping and manipulation of an object by multi-fingered robot hands with rigid or soft hemispheric finger ends that induce rolling contacts with the object. Even in the case of 2D motion like pinching by means of a pair of multi-degrees of freedom robot fingers, there arises an interesting family of Lagrange’s equations of motion with many geometric constraints, which are under-actuated, redundant, and non-holonomic in some sense. Regardless of underactuation of dynamics, it is possible to find a class of sensory feedback signals that realize secure grasp of an object together with control of object orientation. In regard to the secure grasping, a problem of force/torque closure for 2D objects in a dynamic sense plays a crucial role. It is shown that proposed sensory feedback signals satisfying the dynamic force/torque closure can be constructed without knowing object kinematic parameters and location of the mass center. To prove the convergence of motion of the overall fingers–object system under the circumstance of redundancy of joints, new concepts called “stability on a manifold” and “asymptotic stability on a manifold” are introduced. Based on the results found for intelligent control of robotic hands, the last two sections attempt to discuss why human multi-fingered hands can become so dexterous at grasping and object manipulation.     

Painting robot with multi-fingered hands and stereo vision

In this paper, we describe a painting robot with multi-fingered hands and stereo vision. The goal of this study is for the robot to reproduce the whole procedure involved in human painting. A painting action is divided into three phases: obtaining a 3D model, composing a picture model, and painting by a robot. In this system, various feedback techniques including computer vision and force sensors are used. As experiments, an apple and a human silhouette are painted on a canvas using this system.     

A human-like real-time grasp synthesis method for humanoid robot hands

This paper addresses a real-time grasp synthesis of multi-fingered robot hands to find grasp configurations which satisfy the force closure condition of arbitrary shaped objects. We propose a fast and efficient grasp synthesis algorithm for planar polygonal objects, which yields the contact locations on a given polygonal object to obtain a force closure grasp by a multi-fingered robot hand. For an optimum grasp and real-time computation, we develop the preference and the hibernation process and assign the physical constraints of a humanoid hand to the motion of each finger. The preferences consist of each sublayer reflecting the primitive preference similar to the conditional behaviors of humans for given objectives and their arrangements are adjusted by the heuristics of human grasping. The proposed method reduces the computational time significantly at the sacrifice of global optimality, and enables grasp posture to be changeable within 2-finger and 3-finger grasp. The performance of the presented algorithm is evaluated via simulation studies to obtain the force-closure grasps of polygonal objects with fingertip grasps. The architecture suggested is verified through experimental implementation to our developed robot hand system by solving 2- or 3-finger grasp synthesis.     

Task-based compliance planning for multi-fingered robotic manipulations

Based on the analysis of the stiffness relation between the operational space and the fingertip space of multi-fingered hands, this paper provides a guideline of task-based compliance planning for multi-fingered robotic manipulations. In order to show the characteristics of the taskbased stiffness matrix, various two- and three-dimensional examples are illustrated. Also, it is shown that some of the coupling stiffness elements cannot be planned arbitrarily due to grasping geometry. Through the analytical results, it is concluded that the operational stiffness matrix should be carefully specified by considering the location of the compliance center and the grasp geometry of multifingered hands for successful grasping and manipulation tasks.     

气动机器人多指灵巧手——ZJUT Hand

总结了现有灵巧手的缺点,例如结构复杂、难以控制等,并在此基础上提出了一种新型的气动驱动多指灵巧手,命名为ZJUT Hand.基于一种新型的气动柔性驱动器FPA,设计了气动刚柔性弯曲关节及侧摆关节;在此基础上给出了一种4自由度气动拟人手指;为了获得较高的模块化集成度,将5个完全相同的手指装配在拟人手掌上,构成具有5个手指、20个自由度的ZJUT Hand的本体结构;采用仿生学优化方法确定ZJUT Hand的结构参数,并对其本体结构进行了抓持仿真实验.仿真结果表明:ZJUT Hand能够对圆柱、长条形、球形等典型形状的物体实现抓持,并能够模拟人手实现对捏、夹持、勾拉等复杂拟人手形.详细设计了ZJUT Hand的力/位传感系统.完成了ZJUT Hand的抓取实验,结果表明:ZJUT Hand能够对典型形状目标物体实现稳定抓取.最后,简单总结了ZJUT Hand的特色之处.     

Control of twisting manipulation using a multi-fingered robotic hand with a common rotational axis

The main purpose of the present study is to prove the usability of a mechanism with a common rotational axis during twisting manipulation using a multi-fingered robotic hand where two fingers and two other fingers can independently rotate in inner and outer circles with a dual turning mechanism. Although various types of conventional multi-fingered hands have potential capability to achieve twisting manipulations such as opening a bottle cap from within a hand, it is well-known that such tasks are difficult to execute quickly due to limited working space of the fingers and complexity of control. The proposed hand with a common rotational axis is effective in rotational manipulation around a particular axis, where each joint role assignment is completely decoupled into internal force control for grasping an object and velocity control around the axis for rotating the object. We prove the usability of this mechanism with a common rotational axis through the use of a control scheme, and show experimental results involving manipulation tasks where twisting manipulation is dominant.

     

力触觉反馈装置发展概述

力触觉反馈技术起源于主从机器人领域,能够给操作者带来真实沉浸的体验,提高操作效率。近年来,随着遥操作、虚拟现实等技术的发展,力触觉反馈装置得到了研究人员的高度关注。首先,简要总结了力触觉反馈技术的发展状况;然后,对现有力触觉反馈装置进行了分类,介绍了近年来力触觉反馈装置的研究情况;最后,针对现有研究,分析和阐述了力触觉反馈装置的发展趋势,并指出了目前存在的问题,对力触觉反馈装置未来所面临的机遇与挑战提出了一些见解。