检索结果-内蒙古大学图书馆

13th International Conference on Pattern Recognition, ICPR 1996

作者： Ude, Aleš Ekre, Tor Eivind Institute for Real-Time Computer Systems and Robotics University of Karlsruhe Kaiserstr. 12 76128 Karlsruhe Germany

ISBN: (纸本)081867282X

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. © 1996 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Sensor system and powerful computer system for controlling a microrobot-based micromanipulation station

引用

JOURNAL OF MICROMECHANICS AND MICROENGINEERING 1997年第3期7卷 256-258页

作者： Fischer, T Santa, K Fatikow, S University of Karlsruhe Department of Computer Science Institute for Real-Time Computer Systems and Robotics Kaiserstr.12/Geb. 40.28 D-76128 Karlsruhe Germany Presented on 22 October 1996 accepted for publication 8 April 1997

Mobile microrobots, which are capable of performing microscopic motions, have become a subject of great interest all over the world, They have the potential to be used for a variety of applications: in industry for assembly of microsystems or for the testing of silicon chips;in medicine for handling biological cells, etc. A new model of an automated micromanipulation station, which includes piezoelectric microrobots is now being built by an interdisciplinary research group at the University of Karlsruhe, Germany, This paper describes a sensor system and a powerful tailorable computer for controlling the micromanipulation station.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

computer Aided Layout Planning for Robot Assembly Applications

引用

IFAC Proceedings Volumes 1990年第3期23卷 159-164页

作者： M. Huck Institute for Real-time Computer Control Systems and Robotics Faculty for Informatics University of Karlsuhe Karlsruhe FRG

This paper presents ROSI-Layout, a computer aided planning system for the generation of suitable workcell layouts for robot assembly applications. The idea is to derive first the spatial transformations for the product parts, which lead to the assembly of the final product. A global database provides the product data and the precedence graph. This information comes from product design and assembly planning. The design of spatial transformations is derived from constraints given by the geometric shape of the product parts and from rules that define how assembly with robots should be accomplished. This is followed by the generation of a suitable layout. A layout can be developed that is specially designed for the product to be assembled. During the entire planning session, the database manages all planning data and ensures consisteny. ROSI-Layout is an extension of the RObot Simulation system ROSI.

关键词： computer-aided planning workcell design layout planning robot assembly robot simulation assembly planning work frame data model

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Strategies for Knowledge Acquisition in Autonomous Robot systems

引用

IFAC Proceedings Volumes 1988年第16期21卷 5-15页

作者： R. Dillmann Institute for Real-Time Computer Control and Robotics University of Karlsruhe Karlsruhe FRG

Machine learning has been studied for more than 20 years. Most of the recent research contributions are basic and come from the areas of Cognitive Science and Artificial Intelligence. The classical domain of machine learning is related to vision and image analysis and image description. Since about five years there has been encreased activity to apply and to extend these general learning methods to really complex systems such as autonomous robots. The purpose of applied machine learning methods is to facilitate and to aid automatic construction and generation of knowledge based systems and to increase the system performance with time. Autonomous robot systems will operate in an unknown real environment and are based on the interaction of the basic system components such as action planner, plan executive and action monitor which need knowledge about the real world and knowledge about how to behave to reach a given goal. A robot system can learn if it is able to make changes and extensions in its behavioural control structure that enables it to better perform a given task. This includes acquisition of declarative procedural knowledge, the developement of manipulative and cognitive skills through instruction and practice as well as the organisation of knowledge into efficient representations. The purpose of automatic self-configurating or self-modifying representations is to make experience based knowledge available for possible future use in the context of increasing robot system performance. This paper reviews some general methods of machine learning application and some first results achieved to date.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation of Vision in Robot Applications

引用

IFAC Proceedings Volumes 1988年第16期21卷 499-504页

作者： J. Raczkowsky K.H. Mittenbühler C. Fohler Institute for Real-Time Computer Control Systems and Robotics Faculty for Informatics University of Karlsruhe 7500 Karlsruhe FRG

This paper describes a method to simulate vision for use in robot applications. Our approach shows the physical modeling of the camera, the light sources and the objects within the scene based on a geometric model. Many parameters of the physical model may be adjusted to obtain simulation results close to reality. For processing of the picture data the SPIDER program is added to the simulation of the camera. Though a complete vision system is created. An example shows the simulation of a CCD-camera and a scene with workpieces taken from the ‘European Benchmark’ [COL85].

关键词： Sensors simulation robotics vision CAD modeling picture processing

来源：评论

学校读者我要写书评

暂无评论

Motivation and Competitive Learning in a Social Robot

Motivation and Competitive Learning in a Social Robot

引用

IEEE/RSJ International Conference on Intelligent Robots and systems

作者： Dominguez, Salvador Zalama, Eduardo Garcia-Bermejo, Jaime G. Pulido, Jaime CARTIF Foundation Robotics Computer Vision and Real Time Division Boecillo Valladolid Spain University of Valladolid (Spain) Dep. of Systems Engineering and Automatic Control Industrial Engineering School Spain

ISBN: (纸本)9781424420575

This paper describes the motivation and learning subsystems of Arisco which is a mechatronic head with interactive capacity which includes high expressivity through gesturing, voice recognition, text to speech generation, visual tracking, and internet information retrieval. The general architecture is first described in the paper. Then, the learning capacity of Arisen is addressed. It learns and performs associations between different stimulus responses through several dynamic neural networks, guided by motivational drives. A number of experiments are discussed, covering stimulus competition, habituation, classical and operant conditioning.

关键词： Social robot learning interaction computer vision motivation

来源：评论

学校读者我要写书评

暂无评论

Efficient TD3 based path planning of mobile robot in dynamic environments using prioritized experience replay and LSTM

引用

Scientific reports 2025年第1期15卷 18331页

作者： Yunhan Lin Zhijie Zhang Yijian Tan Hao Fu Huasong Min School of Computer Science and Technology Wuhan University of Science and Technology Wuhan 430081 China. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan 430081 China. Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan 430081 China. Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan 430081 China. mhuasong@***.

To address the challenges of sample utilization efficiency and managing temporal dependencies, this paper proposes an efficient path planning method for mobile robot in dynamic environments based on an improved twin delayed deep deterministic policy gradient (TD3) algorithm. The proposed method, named PL-TD3, integrates prioritized experience replay (PER) and long short-term memory (LSTM) neural networks, which enhance both sample efficiency and the ability to handle time-series data. To verify the effectiveness of the proposed method, simulation and practical experiments were designed and conducted. In the simulation experiments, both static and dynamic obstacles were included in the test environment, along with experiments to assess generalization capabilities. The algorithm demonstrated superior performance in terms of both execution time and path efficiency. The practical experiments, based on the assumptions from the simulation tests, further confirmed that PL-TD3 has improved the effectiveness and robustness of path planning for mobile robot in dynamic environments.

关键词： Long short-term memory (LSTM ) Path planning in dynamic environment Prioritized experience replay (PER) Reinforcement learning Twin delayed deep deterministic policy gradient (TD3) algorithm

来源：评论

学校读者我要写书评

暂无评论

Dealing with unexpected situations during the execution of robot motions

Dealing with unexpected situations during the execution of r...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： M. Spreng Institute for Real-Time Computer Control Systems and Robotics University of Karlsruhe Karlsruhe Germany

The problem of a polygonal object moving in an uncertain polygonal environment, i.e. the positions and orientations of the objects relative to each other are not exactly known, is addressed. Furthermore, the moving object does not move exactly as it is commanded to move. Due to these uncertainties, even a motion generated by a correct motion planner may fail, i.e. for instance, an unexpected contact may occur. A situation analyzer that enables the moving object to acquire information on a contact situation is presented. This analyzer uses the nominal world model including information on the magnitude of the uncertainties in order to get hypotheses on the geometric entities involved in the contact. The discrimination among the hypotheses is based on test motions, i.e. motions whose feasibility depends on the validity of a certain subset of the hypotheses.< >

关键词： Uncertainty Testing Information analysis Robotic assembly real time systems Motion control Robot control control systems Solid modeling Environmental economics

来源：评论

学校读者我要写书评

暂无评论

Online planning of action sequences for a two-arm manipulator system

Online planning of action sequences for a two-arm manipulato...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： A. Hormann U. Rembold R. Dillmann Institute for Real-Time Computer Control Systems and Robotics University of Karlsruhe Karlsruhe Germany

F/sub A/TE, an online task-level planning system for an advanced assembly robot consisting of two manipulators and a set of different sensors such as an overhead camera and force-torque sensors, is presented. The planning system takes an implicit description of the assembly task, plans a sequence of explicit robot commands and monitors the execution by the real-time robot control system. Because it runs completely online, the planning process is highly reactive using sensor information about the robot's present environment. This planning integrates as a key feature a dynamic mapping of assembly subtasks ready for execution onto the manipulators available at the moment. The system was implemented in Prolog on a SUN 4/75 SPARCstation running Unix.< >

关键词： Robotic assembly Sensor systems Robot sensing systems Manipulator dynamics Tellurium Robot vision systems Cameras Assembly systems real time systems Robot control

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：