An adaptive learning control approach is proposed which combines a mechanism to improve the control input sequence as well as to improve the learning control scheme based on the knowledge learned about the unknown sys...
详细信息
An adaptive learning control approach is proposed which combines a mechanism to improve the control input sequence as well as to improve the learning control scheme based on the knowledge learned about the unknown system and environment. The iterative learning control problem is treated from the 2D system point of view. A 2D model for a class of iterative learning control system is formulated. A learning gain estimator algorithm based on the 2D model is presented. The overall learning control system structure is given. The proposed learning control scheme does not require prior knowledge of the controlled system and has the ability to generalize the knowledge learned from one task operation to other tasks. This scheme can be applied to nonlinear system control problems. To demonstrate the feasibility of the proposed learning algorithm, simulation results on learning control for a three-water-tank system are given. The results show an excellent learning performance, even for nonrepetitive tasks.< >
An adaptive learning control approach is proposed that combines a mechanism to improve control input sequence as well as to improve the learning control scheme based on the knowledge learned about unknown system and e...
详细信息
An adaptive learning control approach is proposed that combines a mechanism to improve control input sequence as well as to improve the learning control scheme based on the knowledge learned about unknown system and environment. First, the iterative learning control problem is treated from the 2-D system point of view. A 2-D model for a class of iterative learning control systems is formulated. Then a learning gain estimator algorithm based on the 2-D model is presented. The overall learning control system structure is given.< >
An efficient planning algorithm for the organization and formulation of complete plans applicable to both robotic assemblies and intelligent robotic systems is proposed. The constraint of task precedence and the conce...
详细信息
An efficient planning algorithm for the organization and formulation of complete plans applicable to both robotic assemblies and intelligent robotic systems is proposed. The constraint of task precedence and the concepts of the criticality of tasks-events and valid repetitive orderings are introduced to facilitate and optimize the formulation of every complete plan capable of executing a user-requested job. Two examples demonstrate the applicability of the proposed algorithm to both robotic assemblies and intelligent robotic systems.
Sensing is one of the most essential aspects of any robotic application, be it manufacturing or any automated process. Robotic sensors can be divided into two classes of " internal " and " external &quo...
详细信息
Sensing is one of the most essential aspects of any robotic application, be it manufacturing or any automated process. Robotic sensors can be divided into two classes of " internal " and " external ". Examples of the first group are position or velocity, while the second group includes proximity, touch, or vision to name a few. The other important problem in manufacturing is interfacing with the environment within a cell. The object of this tutorial paper is to survey the two issues of "sensing" and "interfacing" in robotics and manufacturing.
An approach to intelligent PID (proportional integral derivative) control of industrial systems which is based on the application of fuzzy logic is presented. This approach assumes that one has available nominal contr...
详细信息
An approach to intelligent PID (proportional integral derivative) control of industrial systems which is based on the application of fuzzy logic is presented. This approach assumes that one has available nominal controller parameter settings through some classical tuning technique (Ziegler-Nichols, Kalman, etc.). By using an appropriate fuzzy matrix (similar to Macvicar-Whelan matrix), it is possible to determine small changes on these values during the system operation, and these lead to improved performance of the transient and steady behavior of the closed-loop system. This is achieved at the expense of some small extra computational effort, which can be very easily undertaken by a microprocessor. Several experimental results illustrate the improvements achieved.< >
The design and implementation of flexible manufacturing systems require the planning of task requirements to meet standards of reliability, cost, and throughput over a family of products. Tools for computer-aided engi...
详细信息
In this paper, a novel approach to solve the mobile robot path planning problem in an unknown environment is presented. Inherently, the obstacle information from robot perception is contaminated with uncertainties, an...
详细信息
To improve the performance of autonomous vehicles operating in a factory environment, it is important to develop an intelligent planning system to avoic. vehicle collisions as well as to design a good path network whi...
详细信息
Surface reconstruction from cross-sectional contours has become increasingly important in medical image applications. In this paper, a method of reconstructing the surface of an object based on the descriptions of cro...
详细信息
The objective of this paper is to present a 3D object recognition system with emphasis on an optimum placement strategy for a mobile 3D range sensor. The theoretical aspects leading to the development of the 3D sensor...
详细信息
暂无评论