检索结果-内蒙古大学图书馆

Intelligent real-time control of a multifingered robot gripper by learning incremental actions

Annual Review in Automatic Programming 1992年 17卷 303-309页

作者： K. Kleinmann M. Hormel W. Paetsch Darmstadt University of Technology Department of Control Systems Theory and Robotics Darmstadt Germany

Learning control systems are expected to have several advantages over conventional approaches when dealing with complex, high-dimensional processes. One example is the task of controlling grasping operations of a multifingered, mul-tijoined robot gripper, which has been designed and implemented at our robotics lab (the Darmstadt-Hand). The Advanced Gripper control with Learning Algorithms-AGRICOLA- presented in this paper is able to maintain a stable grasp even if disturbances are applied. Also it works for objects of different sizes for which the grasping has not been learned. Compared to the conventional stiffness approach the performance of the learning system is equal but the design is much easier, since less knowledge about the gripper-hardware has to be taken into account. The main part of the learning control loop is an associative memory storing the grasping behaviour as determined by the choice of an objective function.

关键词： high-dimensional nonlinear process stable grasp object manipulation associative memories learning control loop

来源：评论

学校读者我要写书评

暂无评论

Stochastic stability of potential function maximizers in continuous version of independent log-linear learning

Stochastic stability of potential function maximizers in con...

引用

European control Conference (ECC)

作者： Tatiana Tatarenko Department of Control Theory and Robotics TU Darmstadt Germany

This paper deals with game theoretic learning in multi-agent systems with continuous action sets. A potential game is considered, in which the potential function is the global objective function to be maximized in the system under consideration. The focus is on the independent log-linear learning procedure whose discrete version was firstly introduced. In this paper we provide the proof of the stochastic stability of potential function maximizers in case of continuous action games. It implies that an appropriate parameter setting guarantees the algorithm convergence to some potential function maximizer with a given in advanced probability p ∈ (0,1). To analyze the stationary distribution of the underlying continuous Markov chain, we develop here a new method that enables to approximate the initial continuous chain by chains whose long run properties can be established.

关键词： Games Markov processes Kernel Convergence Stability analysis Multi-agent systems Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A three fingered, multijointed gripper for experimental use

A three fingered, multijointed gripper for experimental use

引用

1990 IEEE International Workshop on Intelligent Robots and Systems, IROS 1990

作者： Paetsch, W. Kaneko, M. Technical University of Darmstadt Department of Control Engeneering Control Systems Theory and Robotics Section Germany Kyushu Institute of Technology Computer Science and System Engeneering Kawazu 680-4 Iizuka820 Japan

A three fingered, multijointed robot gripper for experimental use is presented. The mechanics as well as the control architecture are designed for this special purpose. The gripper system provides the basic means in terms of position and force control to perform experiments about grasping and object motion in a useful way. The gripper will be used to develop and evaluate different approaches of stable grasping and object manipulation. First results of the control of the gripper on joint level as well as the cartesian behaviour of the fingers and some results and experiences with first grasping and manipulation experiments using the presented system are reported. © 1990 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Some approaches to context based grasp planning for a multi-fingered gripper

Some approaches to context based grasp planning for a multi-...

引用

IEEE International Workshop on Intelligent Robots and Systems (IROS)

作者： M. Seitz J. Kraft Control Systems Theory & Robotics Department Darmstadt University of Technology Germany

Dexterous manipulations of a-priori unknown objects by a multi-fingered gripper require a vision assisted planning of suitable grasps. The selection of the optimum grasp is based on context information specifying the goal of manipulation given by the user, constraints due to the gripper geometry and object properties to be perceived by a vision system. The integration of vision into a hand-arm system allows planning and performance for grasping even unregularly shaped objects. The paper presents a context level for classification of specific grasp situations and a planning level for determination of gripping positions and forces. Especially strategies searching for suitable contact points for the gripper are discussed and compared to each other.< >

关键词： Grippers Shape Information geometry Robotic assembly Technology planning Robots Machine vision Power system modeling Intelligent sensors Fingers

来源：评论

学校读者我要写书评

暂无评论

A simple approach for hand-arm coordination

A simple approach for hand-arm coordination

引用

IEEE International Workshop on Intelligent Robots and Systems (IROS)

作者： W. Paetsch A. Weigl Control System Theory and Robotics Department Technical University of Darmstadt Germany

When integrating a dexterous robot hand into a hand-arm system, one has to coordinate and control the usually redundant system while taking into account the special capabilities of the subsystems "hand" and "arm". This paper presents a simple approach for hand-arm coordination in Cartesian space which subdivides the object motion into hand and arm portions using only a few easily interpretable parameters. Applying well-known stiffness control approaches for the hand and the arm respectively, the problem of controlling the subsystems appropriately (including force control) is solved. The results of experiments using a system with 15 degrees of freedom are shown and discussed.

关键词： Robot kinematics control systems Motion control Jacobian matrices Force control Velocity control Torque control Null space Grasping Joining processes

来源：评论

学校读者我要写书评

暂无评论

On a selftuning decoupling controller for the joint control of a tendon driven multifingered robot gripper

On a selftuning decoupling controller for the joint control ...

引用

IEEE International Workshop on Intelligent Robots and Systems (IROS)

作者： K. Kleinmann R. Wacker Control Systems Theory and Robotics Department Darmstadt University of Technology Germany

This paper discusses couplings between the joints observed during position control using a tendon driven multifingered robot gripper. Depending on the mechanical construction these effects are non-linear and time variant as a consequence of friction and cable tension. Because the quality of the joint control is an important prerequisite for stable grasping, its design has to consider these coupling effects, generally using linear models. Therefore, the paper proposes a selftuning system which performs an iterative identification of a decoupling controller. The controller is stored in a CMAC-based neural network, so it can realize a non-linear decoupling. The authors present experimental results obtained by this method in comparison with a conventional approach.< >

关键词： Tendons Robots Grippers Pulleys control systems Torque control Mechanical cables Fingers Couplings Learning systems

来源：评论

学校读者我要写书评

暂无评论

Towards vision assisted space robotics: some examples and experimental results

Towards vision assisted space robotics: some examples and ex...

引用

IEEE International Workshop on Intelligent Robots and Systems (IROS)

作者： M. Seitz N. Hartwig J. Matthiesen Control Systems Theory and Robotics Department Darmstadt University of Technology Germany

Automatic handling, maintenance and repair procedures in orbital space applications will gain importance in the future. Lightweight space robots could be used for many of these tasks, provided they would be dexterous enough and more flexible in their perception of the working environment than the present ones. The employment of vision enables a robot to grasp, and manipulate inspected objects autonomously. The paper describes the interaction between robot, camera and a multisensory gripper for performance of local repair tasks, e.g. opening the jammed solar panel of a satellite, by 3D active inspection. Central points of interest have been the composition of information acquired from image sequences as well as the object localization in the robot work space and the supervision of grasping procedures. Besides a description of the system structure and the underlying ideas, experiences and results from terrestrial lab experiments are presented in order to discuss the limits and possibilities of the use of vision for space robotic tasks.

关键词： Orbital robotics Robot vision systems robotics and automation Employment Cameras Grippers Jamming Satellites Inspection Image sequences

来源：评论

学校读者我要写书评

暂无评论

Nash Equilibrium Flow in a Routing Game with Random Queues

Nash Equilibrium Flow in a Routing Game with Random Queues

引用

第26届中国控制与决策会议

作者： Tatiana Tatarenko Ivan Popov Department of Control Theory and Robotics TU DarmstadtDarmstadt 64289Germany

ISBN: (纸本)9781479937097

In this paper, we present a new dynamic flow routing model on networks of parallel paths with capacities on edges and a regime of random queues at vertices. According to the introduced rules of waiting at vertices, we estimate the routing cost functions expressed by a mathematical expectation of a routing duration. For the corresponding routing game with nonatomic agents we prove the existence of Nash equilibrium flows and provide a method for their *** a basis of the investigated properties of cost functions and Nash equilibrium flows, we show that the routing costs can be changed in such a way that one of the resulting equilibrium flows minimizes with some accuracy the time a network is used by agents.

关键词： Dynamic Routing,Capacitated Network,Random Queues,Nash equilibrium flow,Price Design.

来源：评论

学校读者我要写书评

暂无评论

Solving insertion tasks with a multifingered gripper by fumbling

Solving insertion tasks with a multifingered gripper by fumb...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： W. Paetsch G. von Wichert Control System Theory and Robotics Department Technical University of Darmstadt Germany

Part mating with a multifingered gripper mainly comprises two areas, i.e., the control of the gripper or hand and the strategies to solve the task. The problem is made more difficult by the uncertainties from mechanical, sensor or control errors within the gripper system or the parts to be assembled. The authors examine how to find and to realize a hand behavior, which solves the task under the assumption that the system is heavily influenced by the uncertainties mentioned. The problem is solved by a force feedback loop, containing a comparatively simple mathematic description of strategies applied in parallel. The proof of the efficiency of the approach is given. Results of various experiments are presented.< >

关键词： Grippers Error correction Uncertainty Mechanical sensors Sensor systems control systems Robotic assembly Force control Torque control Force sensors

来源：评论

学校读者我要写书评

暂无评论

Force-controlled Robotic Deburring

引用

IFAC Proceedings Volumes 1993年第2期26卷 855-858页

作者： M.-H. Liu H. Tolle Control System Theory and Robotics Group Department of Control Engineering Technical University of Darmstadt Schlossgraben 1 Darmstadl Germany

In this paper a three-step active deburring strategy is proposed based on force feedback control. Strategies for automatic contour following are developed to identify unknown workpiece contours, to automatically generate desired robot motions, and to detect unknown burr sizes. Under the active deburring strategy burr size variations are identified through contour following and different sizes of burrs are removed with a specification of a variable desired deburring force. Implementation of and experiments with the proposed strategies are described.

关键词： Deburring force control grinding machining position control robots teaching

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：