Cooperation in learning improves the speed of convergence and the quality of learning. Special care is needed when heterogeneous agents cooperate in learning. It is discussed that, cooperation in learning may cause th...
详细信息
Cooperation in learning improves the speed of convergence and the quality of learning. Special care is needed when heterogeneous agents cooperate in learning. It is discussed that, cooperation in learning may cause the learning process to diverge if heterogeneity is not handled properly. In this paper, it is assumed that two heterogeneous Q-learning agents cooperate to learn. The heterogeneity is assumed in their action order (and not in their action set). A Q-learning-based method is introduced for the agents to learn the mapping among their actions. It is shown that, the agents are able to learn this mapping while cooperating in learning. Some simulation results are reported to show the effectiveness of the proposed method.
Q-learning is widely used in many multi agent systems. In most cases, a separate critic is considered for qualifying each individual agent behavior or it is assumed that the critic is completely aware of effects of al...
详细信息
Q-learning is widely used in many multi agent systems. In most cases, a separate critic is considered for qualifying each individual agent behavior or it is assumed that the critic is completely aware of effects of all agents' actions on the team qualification. But, in many cases, the role of each team member in the group performance is not known. In order to distribute a common credit among the agents, a suitable criterion must be provided to estimate the role of each agent in the team performance and to judge if an agent has done a wrong action. In this paper two such criteria, named certainty and expertness, for a team of agents with parallel tasks are introduced. In addition, two methods for reinforcing the agents based on the proposed measures are provided. Some simulation results are also reported to show the effectiveness of the proposed measures and methods.
In this paper discrete-time iterative learning control (ILC) systems are analysed from an algebraic point of view. The algebraic analysis shows that an ILC synthesis problem can be considered as a tracking problem of ...
详细信息
In this paper discrete-time iterative learning control (ILC) systems are analysed from an algebraic point of view. The algebraic analysis shows that an ILC synthesis problem can be considered as a tracking problem of a multi-channel step-function. Furthermore, the plant to be controlled is a static multivariable plant. Another major contribution of this paper is a general convergence theory of ILC systems in terms of their closed-loop poles. This convergence theory shows that time-variant ILC control laws should be typically used instead of time-invariant control laws in order to guarantee good transient tracking behaviour. Simulations high-light the different theoretical findings in this paper.
An essential factor in understanding the motor learning capability of humans, is the coordinate transformation learning of the visual feedback controller. Although a number of learning models for the visual feedback c...
详细信息
An essential factor in understanding the motor learning capability of humans, is the coordinate transformation learning of the visual feedback controller. Although a number of learning models for the visual feedback controller have been proposed, none has been able to establish a definitive approach. In our previous work, we have suggested a learning model that uses disturbance noise and the feedback error signal to learn the human visual feedback controller's coordinate transformation. However, the model does not fully consider the time delay in the visual feedback control loop. This paper presents a modified learning model taking into account the time delay and the convergence properties of the model. Numerical simulations are presented to illustrate the effectiveness of the proposed approach.
To operate over a long period of time in the real world, autonomous mobile robots must have the capability of recharging themselves whenever necessary. In addition to be able to find and dock into a charging station, ...
详细信息
作者：
A. KoschanSunHo LeeM.A. AbidiImaging
Robotics and Intelligent Systems Laboratory Department of Electrical and Computer Engineering University of Tennessee USA
A new method is presented for the localization and recognition of three-dimensional objects using color information. In the first processing step, we estimate depth information by either applying a chromatic block mat...
详细信息
A new method is presented for the localization and recognition of three-dimensional objects using color information. In the first processing step, we estimate depth information by either applying a chromatic block matching method to color stereo images or acquiring a range image from a laser scanner. Second, the computed depth maps are segmented to distinguish between the image background and the objects that should be recognized. Assuming that the segmented regions represent single objects in the three-dimensional scene, feature vectors are generated based on color histograms. The Euclidean distance is used as well as the scalar product to measure the similarity between the feature vectors computed from the color image and the feature vectors stored in a database.
A global adaptive output feedback dynamic compensator is proposed for stabilization and tracking of a class of systems that are globally diffeomorphic into systems in generalized output-feedback canonical form. This f...
详细信息
A global adaptive output feedback dynamic compensator is proposed for stabilization and tracking of a class of systems that are globally diffeomorphic into systems in generalized output-feedback canonical form. This form includes as special cases the standard output-feedback canonical form and various other forms considered previously in the literature. Output-dependent nonlinearities are allowed to enter both additively and multiplicatively. The system is allowed to contain unknown parameters multiplying output-dependent nonlinearities. Under the assumption that a constant matrix can be found to achieve a certain property, it is shown that a reduced-order observer and a backstepping controller can be designed to achieve asymptotic tracking. It is also shown that this assumption can be removed by introducing extra dynamics. This represents the first adaptive output-feedback tracking results for this class of systems.
The paper presents a number of image processing and pattern recognition applications using coordinate logic filters which execute coordinate logic operations among the pixels of the image. These filters are very effic...
详细信息
ISBN:
(纸本)9539676940
The paper presents a number of image processing and pattern recognition applications using coordinate logic filters which execute coordinate logic operations among the pixels of the image. These filters are very efficient in various 1D, 2D or higher-dimensional digital signal processing applications, such as noise removal, magnification, opening, closing, skeletonization, coding, edge detection, feature extraction, and fractal modeling. The key issue in the coordinate logic analysis of images is the method of fast successive filtering and managing of the residues. The desired processing is achieved by executing only direct logic operations among the pixels of the given image. Coordinate logic filters can be easily and quickly implemented using logic circuits or cellular automata; this is their primary advantage.
A global decentralized adaptive output-feedback dynamic compensator is proposed for stabilization and tracking of a class of large-scale systems that are globally diffeomorphic into systems which are interconnections ...
详细信息
ISBN:
(纸本)0780370619
A global decentralized adaptive output-feedback dynamic compensator is proposed for stabilization and tracking of a class of large-scale systems that are globally diffeomorphic into systems which are interconnections of subsystems in generalized output-feedback canonical form. This form includes as special cases the standard output-feedback canonical form and various other forms considered previously in the literature. Output-dependent nonlinearities are allowed to enter both additively and multiplicatively. The system is allowed to contain unknown parameters multiplying output-dependent nonlinearities, and, also, unknown nonlinearities satisfying certain bounds. Under the assumption that a constant matrix can be found to achieve a certain property, it is shown that reduced-order observers and backstepping controllers can be designed to achieve practical stabilization of the tracking error in each subsystem. Sufficient conditions under which asymptotic tracking and stabilization can be achieved are also obtained. This represents the first decentralized adaptive output-feedback tracking results for this class of systems.
A robust adaptive nonlinear dynamic controller is designed to achieve practical stabilization for position tracking error of a voltage-fed permanent-magnet stepper motor. The control design is an output-feedback desig...
详细信息
A robust adaptive nonlinear dynamic controller is designed to achieve practical stabilization for position tracking error of a voltage-fed permanent-magnet stepper motor. The control design is an output-feedback design that utilizes only rotor positions measurements. Rotor velocity and stator phase currents are not available for feedback. Furthermore, the only motor parameter that is required to be known is the time constant of the electrical subsystem. Adaptations are utilized so that no other knowledge of motor parameters is required. The proposed controller is robust to load torques, friction, cogging forces, and other disturbances satisfying certain bounds. These results can also be extended to other classes of motors.
暂无评论