检索结果-内蒙古大学图书馆

Programming by demonstration: A machine learning approach to support skill acquision for robots 3rd

3rd International Conference on Artificial Intelligence and Symbolic Mathematical Computation, AISMC 1996

作者： Dillmann, R. Friedrich, H. University of Karlsruhe Institute for Real-Time Computer Systems and Robotics Kaiserstr. 12 KarlsruheD-76128 Germany

ISBN: (纸本)3540617329

Programming by Demonstration (PbD) is a programming method that allows to add new functionalities to a system by simply showing the desired task or skill in form of few examples. In the domain of robotics this paradigm offers the potential to reduce the complexity of robot task programming and to make programming more "natural". In case of programming an assembly task PbD allows with the help of a video or a laser camera and a data glove the automatic generation the necessary robot program for the assembly task. In addition, the demonstration of the task with few different assembly situations and strategies may achieve a generalized assembly function for all possible variants of the class. In order to realize such a PbD system at least two major problems have to be solved. First, the sensor data trace of a demonstration has to be interpreted and transformed into a high-level situation-action representation. This task is not yet well understood nor solved in general. Second, if a generalization is required, induction algorithms must be applied to the sensor data trace, to find the most general user-intended robot function from only few examples. In this paper mainly the second problem is focused. The described experimental PbD environment consists of an industrial robot, a 6D space mouse used as input device, and some sensors. Various data can be recorded during a demonstration for further processing in the PbD system implemented on a workstation. The objective is to exploit the possibilities of integrating learning and clustering algorithms for automated robot programming. In particular it is investigated how human interaction with the PbD system as well as user-initiated dialogs can support inductive learning to acquire generalized assembly programs and skills. © Springer-Vedag Berlin Heidelberg 1996.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

THE LIQUID MODEL LOAD BALANCING METHOD

引用

Parallel Algorithms and Applications 1996年第3-4期8卷 285-307页

作者： Dominik Henrich[a] [a] Institute for Real-Time Computer Systems and Robotics Computer Science Department University of Karlsruhe Karlsruhe D Germany

Load balancing is one of the central problems that have to be solved in parallel computation. Here, the problem of distributed, dynamic load balancing for massive parallelism is addressed.A new local method, which realizes a physical analogy to equilibrating liquids in multi-dimensional tori or hypercubes, is presented. It is especially suited for communication mechanisms with low set-up to transfer ratio occurring in tightly-coupled or SIMD systems. By successive shifting single load elements to the direct neighbors, the load is automatically transferred to lightly loaded *** to former methods, the proposed Liquid model has two main advantages. First, the task of load sharing is combined with the task of load balancing, where the former has priority. This property is valuable in many applications and important for highly dynamic load distribution. Second, the Liquid model has high efficiency, Asymptotically, it needsO(D K Ldiff) load transfers to reach the balanced state in aD-dimensional torus withKprocessors per dimension and a maximum initial load difference ofLdiff. The Liquid model clearly outperforms an earlier load balancing approach, the *** a survey of related research, analytical results within a formal framework are derived. These results are validated by worst-case simulations in one- and two-dimeasional tori with up to two thousand processors.

关键词： Distributed computing parallel algorithms load sharing load balancing rings tori hypcrcubes.

来源：评论

学校读者我要写书评

暂无评论

Building elementary robot skills from human demonstration

Building elementary robot skills from human demonstration

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： M. Kaiser R. Dillmann Institute for Real Time Computer Systems & Robotics University of Karlsruhe Karlsruhe Germany

This paper presents a general approach to the acquisition of sensor-based robot skills from human demonstrations. Since human-generated examples cannot be assumed to be optimal with respect to the robot, adaptation of the initially acquired skill is explicitly considered. Results for acquiring and refining manipulation skills for a Puma 260 manipulator are given.

关键词： Humans Robot sensing systems real time systems Robot control Character generation Sensor phenomena and characterization

来源：评论

学校读者我要写书评

暂无评论

A review of parallel processing approaches to motion planning

A review of parallel processing approaches to motion plannin...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： D. Henrich Institute for Real Time Computer Systems and Robotics University of Karlsruhe Karlsruhe Germany

One of the many features needed to support the activities of autonomous systems is the ability of motion planning. It enables robots to move in their environment securely and to accomplish given tasks. Unfortunately, the control loop comprising sensing, planning, and acting has not yet been closed for robots in dynamic environments. One reason involves the long execution times of the motion planning component. A solution for this problem is offered by the use of highly computational parallelism. Thus, an important task is the parallelization of existing motion planning algorithms for robots so that they are suitable for highly computational parallelism. In several cases, completely new algorithms have to be designed, so that a parallelization is feasible. We review approaches to motion planning using parallel computation.

关键词： Parallel processing Process planning Concurrent computing Surface-mount technology Mobile robots Mesh generation Orbital robotics Search methods Broadcasting

来源：评论

学校读者我要写书评

暂无评论

Fuzzy control for mobile manipulation

Fuzzy control for mobile manipulation

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： U.M. Nassal R. Junge Institute for Real-Time Computer Systems and Robotics (IPR) University of Karlsruhe Karlsruhe Germany

Increasing the flexibility of robot systems has been one of the main objectives of robotics research in recent years. There are various approaches to achieve this: increasing fault-tolerance, the development of new actuators and sensors and the use of learning techniques. But the field of operation of such smart systems is still limited to a rather small area. Mobile manipulation is another facet of increasing the flexibility of a robot system. By exploiting the mobility of a platform, the dextrous workspace of manipulators can be considerably increased. One main research topic on mobile manipulation is the decomposition of the motion of the tool-centre-point into manipulator motion and platform motion. In this paper a new online approach to this decomposition is presented which allows the consideration of complex obstacles and multiple manipulators mounted on the platform. A focus of this paper is the presentation of a fuzzy-controller that enables the robot to perform manipulation and locomotion in an integrated manner.

关键词： Fuzzy control Manipulators control systems Mobile robots Robotic assembly Kinematics Gravity Motion planning Path planning Force control

来源：评论

学校读者我要写书评

暂无评论

Compensation of friction in mechanical drives for a three fingered robot gripper

Compensation of friction in mechanical drives for a three fi...

引用

Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96

作者： T. Doersam P. Duerrschmied Department for Computer Science Institute for Real-Time Computer Systems and Robotics University of Karlsruhe Karlsruhe Germany

Performing fine manipulations with multifingered robot hands makes high demands on the control algorithms and the speed of the control computer. Mainly nonlinear friction problems and plant uncertainties require intensive fine-tuning of a controller. This paper gives insight into the frictional behaviour of geared finger links. The behaviour has been approximated by a friction model. Considering the estimated system parameters two kinds of controllers are developed: a simple PD controller with switchable I-part and a PD-controller with a fuzzy friction compensation working in parallel. The results of both controllers are presented and compared in this paper.

关键词： Friction control systems Robots High performance computing Uncertainty Fingers Parameter estimation PD control Fuzzy control Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

An automated microrobot-based desktop station for micro assembly and handling of micro-objects

An automated microrobot-based desktop station for micro asse...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： S. Fatikow U. Rembold Institute for Real-Time Computer Systems and Robotics Faculty for Informatics University of Karlsruhe Karlsruhe Germany

One of the main problems of present-day microsystem technology (MST) is the assembly of a whole microsystem from different micro-components. This paper presents an automated micromanipulation desktop station the main feature of which are piezoelectrically driven microrobots placed on a highly precise x-y table of a microscope. The microrobots can perform high-precise manipulations (with an accuracy of up to 10 nm) and the transport of very small objects (at a speed of several mm/sec). To control the desktop station automatically, a sensor system is provided for fine and for gross positioning of the robots, respectively. Apart from assembly tasks this automated station can be used, for examples, for handling biological cells or testing silicon chips.

关键词： Microscopy Automatic control control systems Sensor systems Robot sensing systems robotics and automation Robotic assembly Biological cells Automatic testing Silicon

来源：评论

学校读者我要写书评

暂无评论

Simultaneous planning and execution in cranio- and maxillofacial surgery

引用

Studies in Health Technology and Informatics 1996年 29卷 435-446页

作者： Bohner, Petra Pokrandt, Peter Hassfeld, Stefan Institute for Real-Time Computer Systems and Robotics University of Karlsruhe D-76128 Karlsruhe Germany Clinic for Maxillofacial and Craniofacial Surgery University of Heidelberg D-69120 Heidelberg Germany

This paper describes the development of a system for simultaneous planning and execution of surgical operations in the cranio-maxillo facial area. Simultaneous planning and execution is the process of taking an implicit task description, planning a sequence of explicit execution commands e.g. for robots and monitoring their execution. As the execution planning process is running completely on-line, that means during the actual execution of the assembly task, the planning process is highly reactive based on sensor information about the robot's present environment. In order to meet the problem that medical data is usually complex and needs time-costly preprocessing an appropriate architecture for evaluating sensor data has been developed. In this paper, a detailed presentation of the phases of execution planning and sensor data evaluation is given. As an example, the execution of a LeFort I osteotomy is presented. © The authors 1996.

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Learning coordination skills in multi-agent systems

Learning coordination skills in multi-agent systems

引用

Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96

作者： M. Kaiser R. Dillmann H. Friedrich I. Lin F. Wallner P. Weckesser Institute for Real-Time Computer Systems and Robotics University of Karlsruhe Karlsruhe Germany Karlsruher Institut fur Technologie - Campus Nord Eggenstein-Leopoldshafen Baden-WÃ¼rttemberg DE

While distributed control architectures have many advantages over centralized ones, such as their inherent modularity and fault tolerance, a major problem of such architectures is to ensure the goal-oriented behaviour of the controlled system. This paper presents a framework within which the coordination skills required for goal-orientedness are learned from user demonstrations. The framework is based on a state-space model of the single agents building the system and a corresponding model of the coordination mechanism. Our mobile robot PRIAMOS provides an application example.

关键词： Multiagent systems real time systems Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

Stereo grouping for model-based recognition

Stereo grouping for model-based recognition

引用

International Conference on Pattern Recognition

作者： A. Ude T.E. Ekre Institute for Real-Time Computer Systems and Robotics University of Karlsruhe Karlsruhe Germany Karlsruher Institut fur Technologie - Campus Nord Eggenstein-Leopoldshafen Baden-WÃ¼rttemberg DE

A strategy for the fusion of information from a stereo image pair for model-based object recognition is discussed. Our scheme combines a new method for feature grouping with a region-based stereo matching and a hypothesize-and-verify paradigm. The grouping method developed is based on a graph theoretical algorithm. It exploits prior knowledge to find the groups of image features which are likely to come from a sought model(s). The Bayesian classification is used to deal with the resulting hypotheses. A mechanism for a dynamic threshold modification is incorporated into the system to enable the grouping at different resolutions. Unlike classical techniques for object recognition from stereo, our strategy does not depend on a data driven computation of a depth map. We argue that a propulsive reconstruction of 3D information can be more efficient and robust.

关键词： Stereo vision Object recognition Data mining Image segmentation Data structures Indexing real time systems Robots Bayesian methods Image reconstruction

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：