检索结果-内蒙古大学图书馆

Connectionist reinforcement learning of robot control skills

AIP Conference Proceedings 1998年第1期437卷 364-374页

作者： Rui Araújo Urbano Nunes A. T. de Almeida Institute of Systems and Robotics (ISR) Electrical Engineering Department University of Coimbra Pólo II Pinhal de Marrocos 3030 Coimbra-Portugal

Many robot manipulator tasks are difficult to model explicitly and it is difficult to design and program automatic control algorithms for them. The development, improvement, and application of learning techniques taking advantage of sensory information would enable the acquisition of new robot skills and avoid some of the difficulties of explicit programming. In this paper we use a reinforcement learning approach for on-line generation of skills for control of robot manipulator systems. Instead of generating skills by explicit programming of a perception to action mapping they are generated by trial and error learning, guided by a performance evaluation feedback function. The resulting system may be seen as an anticipatory system that constructs an internal representation model of itself and of its environment. This enables it to identify its current situation and to generate corresponding appropriate commands to the system in order to perform the required skill. The method was applied to the problem of learning a force control skill in which the tool-tip of a robot manipulator must be moved from a free space situation, to a contact state with a compliant surface and having a constant interaction force.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of the rapid flight test prototyping system for unmanned air vehicles

Development of the rapid flight test prototyping system for ...

引用

American Control Conference (ACC)

作者： E. Hallberg I. Kaminer A. Pascoal Department of Aeronautical and Astronautical Engineering Naval Postgraduate School Monterrey CA USA Department of Electrical Engineering and Institute for Systems and Robotics (ISR) Instituto Superior Technico Lisboa Portugal

This paper describes the development of a rapid prototyping system for flight testing of guidance, navigation, and control algorithms for unmanned air vehicles. The system affords a small team the ability to take a new concept in guidance, navigation, and control from initial conception to flight test. In order to do this, a number of engineering problems had to be overcome addressing a gamut of issues including weight, power, portability, risk, electronic interference, vibration, manpower, etc. The main contribution of the paper is the proof of concept flight test demonstration of a new integrated guidance and control algorithm.

关键词： System testing Prototypes Navigation Control systems Unmanned aerial vehicles Aerospace engineering Automotive engineering Design engineering Power engineering and energy Aerospace electronics

来源：评论

学校读者我要写书评

暂无评论

Map building using fuzzy ART, and learning to navigate a mobile robot on an unknown world

Map building using fuzzy ART, and learning to navigate a mob...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： R. Araujo A.T. de Almeida Dept. of Electr. Eng. Coimbra Univ. Portugal Institute for Systems and Robotics (ISR) and Electrical Engineering Department University of Coimbra Portugal

This paper introduces a new approach, based on the application of the fuzzy ART neural architecture, for online map building from actual sensor data collected with a mobile robot. This method is then integrated as a complement, on the parti-game learning approach, allowing the system to make a more efficient use of collected sensor information. Also, a predictive online trajectory filtering method is introduced on the learning approach. Instead of having a mechanical device (robot) moving to search the world the idea is to have the system analysing trajectories in a predictive mode, by taking advantage of the improved world model. The real robot will only move to try trajectories that have been predicted to be successful, allowing lower exploration costs. This results on an overall new and powerful method for simultaneous and cooperative construction of a world model, and learning to navigate from an initial position to a goal region on an unknown world. It is assumed that the robot knows its own current world location. It is additionally assumed that the mobile robot is able to perform sensor-based obstacle detection (not avoidance), and straight-line motions. Results of experiments with a real Nomad 200 mobile robot will be presented, demonstrating the effectiveness of the proposed methods.

关键词： Subspace constraints Navigation Mobile robots Trajectory Robot sensing systems Buildings Mechanical sensors Sensor systems Filtering Predictive models

来源：评论

学校读者我要写书评

暂无评论

Fuzzy ART based approach for real-time map building

Fuzzy ART based approach for real-time map building

引用

International Workshop on Advanced Motion Control (AMC)

作者： R. Araujo A.T. de Almeida Dept. of Electr. Eng. Coimbra Univ. Portugal Institute for Systems and Robotics (ISR) and Electrical Engineering Department University of Coimbra Coimbra Portugal

In order to perform complicated tasks in previously unknown indoor environments, autonomous mobile robots must be able to acquire models of their environments. The model or map, is often used for planning robot motions which perform a task while avoiding obstacles in the environment. Applications where there is no previously available world model usually rely on sensor systems, such as laser range finders, and infrared and sonar range sensors, to collect thousands of range points which are difficult to handle and interpret. The paper introduces an approach, based on the fuzzy ART neural architecture, for online map building. The map is incrementally constructed in real-time by fitting rectangular geometrical primitives to actual sensor data collected with a mobile robot. This results in a compact world model that is easy to integrate into planning approaches. A sensor data filtering approach is proposed to reject noisy range points. It is assumed that the robot knows its own current world location. Results of experiments with a real Nomad 200 mobile robot are presented, demonstrating the operation of the proposed map building method.

关键词： Subspace constraints Mobile robots Infrared sensors Indoor environments Motion planning Robot motion Sensor systems Laser modes Sonar applications Sensor systems and applications

来源：评论

学校读者我要写书评

暂无评论

Kinematic manipulability of general constrained rigid multibody systems

Kinematic manipulability of general constrained rigid multib...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： J.T. Wen L.S. Wilfinger Center for Advanced Technology in Automation Robotics & Manufacturing Department of Electrical Computer & Systems Engineering Rensselaer Polytechnic Institute RPI Troy NY USA

Extends the kinematic manipulability concept commonly used for serial manipulators to general constrained rigid multibody systems. Examples of such systems include multiple cooperating manipulators, multiple fingers holding a payload, multi-leg walking robots, and variable geometry trusses. Explicit formulas for velocity and force manipulability ellipsoids are derived and their duality explained. The concept of unstable grasp and manipulable grasp are also extended and illustrated with examples.

关键词： Kinematics Torque Ellipsoids Manufacturing automation robotics and automation computer aided manufacturing Manipulators Fingers Legged locomotion Robots

来源：评论

学校读者我要写书评

暂无评论

Kinematic analysis and position/force control of the anthrobot dextrous hand

引用

IEEE TRANSACTIONS ON systems MAN AND CYBERNETICS PART B-CYBERNETICS 1997年第1期27卷 95-104页

作者： Kyriakopoulos, KJ VanRiper, J Zink, A Stephanou, HE New York State Center for Advanced Technology in Automation and Robotics and Electrical Department of Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA

The increasing demand for robotic applications in unstructured environments is motivating the need for dextrous end-effecters which can cope with the wide variety of tasks and objects encountered in these environments, A new anthropomorphic robot hand (Anthrobot) which was designed for these environments is described. In this paper, the problem of developing the kinematics and unit consistent hybrid position/force control of the Anthrobot fingers is considered as the first step toward its utilization for either teleoperation or autonomous operation, A dynamic model of the fingers is identified and used to develop the control laws, The experimental results of applying the control to the Anthrobot are discussed.

关键词： Kinematics Force control Fingers robotics and automation Robots Humans Thumb Anthropomorphism Vehicle dynamics Power system modeling

来源：评论

学校读者我要写书评

暂无评论

Visual Behaviors for Real-Time Control of a Binocular Active Vision System

引用

IFAC Proceedings Volumes 1997年第3期30卷 167-172页

作者： Jorge Batista Paulo Peixoto Helder Araújo ISR - Institute of Systems and Robotics Department of Electrical Engineering - FCTUC University of Coimbra Portugal

An active vision system has to enable the implementation of reactive visual processes and of elementary visual behaviors in real time. Therefore the control architecture is extremely important. In this paper we discuss a number of issues related with the implementation of a real-time control architecture and describe the architecture we are using with our camera heads. Even though in most applications a fully calibrated system is not required, we also describe a methodology for calibrating the camera head, taking advantage of its degrees of freedom. These calibration parameters are used to evaluate the performance of the system. Another important issue of the operation of active vision binocular heads is their integration into more complex robotic systems. We claim that higher levels of autonomy and integration can be obtained by designing the system architecture based on the concept of purposive behavior. At the lower levels we consider vision as a sensor and integrate it in control systems (both feed-forward and servo loops) and several visual processes are implemented in parallel, computing relevant measures for the control process. At higher levels the architecture is modeled as a state transition system. Finally we show how this architecture can be used to implement a pursuit behavior using optical flow. Simultaneously vergence control can also be performed using the same visual processes.

关键词： Active Vision Real-Time Tracking Smooth-Pursuit

来源：评论

学校读者我要写书评

暂无评论

An Extended Kalman Filter for frequent local and infrequent global sensor data fusion

An Extended Kalman Filter for frequent local and infrequent ...

引用

Conference on Sensor Fusion and Decentralized Control in Autonomous Robotic systems

作者： Roumeliotis, SI Bekey, GA Department of Electrical Engineering Department of Computer Science Institute for Robotics and Intelligent Systems University of Southern California Los Angeles CA 90089-0781 United States

ISBN: (纸本)0819426415

In this paper we compare the performance of a dead-reckoning system for robot navigation to a system using an Extended Kalman Filter (EKF). Dead-reckoning systems are able to approximate position and orientation by feeding data (provided usually by local sensors) to the kinematic model of the vehicle. These systems are subject to many different sources of error. EKFs have the ability to combine the same information and compensate for most of these errors to yield a better estimate. Our simulation results using a simplified kinematic model of Rocky 7 (an experimental rover used in the Mars exploration program at Jet Propulsion Laboratory (JPL)) show that an improvement in performance up to 40% (position error) can be achieved. The local sensors used are: wheel encoders, steering angle potentiometer and gyroscope. Involvement of global sensor measurements can drastically increase the accuracy of the estimate. The lack of GPS or magnetic field on Mars narrows our choices for global localization. Landmarks, such as the sun can be used as natural beacons (reference point for absolute measurements). A sun sensor (SS) that measures the absolute orientation of the rover has been built by Lockheed Martin and now is part of the sensor suite of Rocky 7. The SS measurement is crucial for the estimation filter and we show that the accuracy of the estimation decreases exponentially as the frequency of the SS data fed to the EKF decreases.

关键词： robot localization sun sensor Extended Kalman Filter

来源：评论

学校读者我要写书评

暂无评论

Building a Teleoperation Environment

引用

IFAC Proceedings Volumes 1997年第3期30卷 173-178页

作者： R. Cortesão R. Araújo U. Nunes A.T. de Almeida Institute of Systems and Robotics (ISR)- Electrical Engineering Department University of Coimbra 3030 Coimbra Portugal.

There is a growing need for humans to perform complex remote operations and to extend the intelligence and experience of experts to distant applications. Because of the complex nature of the tasks that usually telerobots perform, centralised control is no longer practical. This motivates the need for an interprocess communication facility. Continuous human operator control in teleoperation has both advantages and disadvantages. The main advantage is that overall task control can rely on human perception, judgement, decision, dexterity, and training. The main disadvantage is that the human operator must cope with a sense of remoteness, be alert of and integrate many information, and coordinate the control of one or two mechanical arms, each having typically six degrees of freedom. A good graphic environment at the local station is needed, to improve the teleoperation tasks. For this reason, computer graphics play an increasingly important role in advanced teleoperation. This paper describes a communication system for a robotic teleoperation environment, how to build a virtual environment of the remote station, and also new scientific visualisation techniques for real time data, using powerful graphical toolkits.

关键词： Communications Virtual Robot Teleoperation Graphic Environment

来源：评论

学校读者我要写书评

暂无评论

Path planning-by-learning with a Nomad 200 mobile robot

Path planning-by-learning with a Nomad 200 mobile robot

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： R. Araujo A.T. de Almeida Institute of Systems and Robotics ISR Electrical Engineering Department University of Coimbra Coimbra Portugal

In this article, the authors face the problem of navigating a mobile robot on an indoor environment, where the location and shape of obstacles is assumed to be initially unknown to the robot. They describe an approach for simultaneous learning of a world model, and learning to navigate from a start position to a goal region on the world. These two learning abilities may be seen as cooperating and enhancing each other in order to improve the overall system performance. It is assumed that the robot knows its own current world position. It is only additionally assumed that the mobile robot is able to perform sensor-based obstacle detection (not avoidance), and that it is able to perform straight-line motions. Results of simulation experiments are presented that demonstrate the effectiveness of the approach to navigate a Nomad 200 mobile robot.

关键词： Mobile robots Robot sensing systems Navigation Robot programming Robot control Control systems Educational robots Indoor environments Shape System performance

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：