Reinforcement Learning (RL) has been applied to robotic arm control, which enables the agent to learn an effective policy to solve complex tasks. However, it requires constant interaction with the environment leading ...
Reinforcement Learning (RL) has been applied to robotic arm control, which enables the agent to learn an effective policy to solve complex tasks. However, it requires constant interaction with the environment leading to low sample efficiency. In this paper, we propose a robotic arm control approach based on planning via lookahead search, which is a model-based RL algorithm to improve the sample efficiency. The approach builds an environment model in order to obtain the dynamics of the environment. Thus the model can be used to plan future actions by a tree-based search. The experiments show that our approach can solve the task of robotic arm control with less environmental samples.
The models for the stress-strain relationship under elevated temperatures and thermal properties of recycled aggregate concrete (RAC) are essential in the fire resistance design of RAC structures, while no such models...
详细信息
This paper is concerned with the problem of H ∞ filtering for discrete-time Takagi-Sugeno (T-S) fuzzy Itô stochastic systems with time-varying delay. Attention is focused on the design of a fuzzy-rule-dependent...
详细信息
This paper is concerned with the problem of H ∞ filtering for discrete-time Takagi-Sugeno (T-S) fuzzy Itô stochastic systems with time-varying delay. Attention is focused on the design of a fuzzy-rule-dependent H ∞ filter such that the filter error system is mean-square asymptotically stable and preserves a prescribed noise attenuation level in the H ∞ sense. Delay-dependent criterion is established for the filter error system without ignoring any useful terms in the derivative of Lyapunov functional, which is dependent on the lower and upper delay bounds. The developed theoretical results are expressed in terms of linear matrix inequalities (LMIs) and can be obtained from the solution of a convex optimization problem. An illustrative numerical example is provided to demonstrate the effectiveness of the proposed method.
This paper presents a sliding mode control (SMC) design method for single input linear systems with uncertainties and time delay in the state. We define a sliding surface for the augmented system with a virtual state ...
详细信息
ISBN:
(纸本)0780364953
This paper presents a sliding mode control (SMC) design method for single input linear systems with uncertainties and time delay in the state. We define a sliding surface for the augmented system with a virtual state which is defined from the nominal system. We make a virtual state from LQR (linear quadratic regulator) gain and the states of the nominal system. We construct a controller that combines SMC with LQR controller. The proposed sliding mode controller guarantees the stability of the overall closed-loop system.
Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to do...
详细信息
The main goal of this paper studies modeling of a direct current coaxial motor (DCCM) and testing the main parameters of DCCM on the experimental model. The DCCM contains two rotors named inner runner and outer runner...
详细信息
The main goal of this paper studies modeling of a direct current coaxial motor (DCCM) and testing the main parameters of DCCM on the experimental model. The DCCM contains two rotors named inner runner and outer runner. The inner runner and the outer runner rotate in opposite directions to each other. The shaft of the inner runner and the shaft of the outer runner are coincident and inserted on two separate bearings. To prove this idea, the mathematic model is achieved by a combination of a mathematic model of DC motor and mathematic model of single phase coaxial motor. Simulation result of the mathematic model in Matlab shows the truth of the hypothesis of the design. The result of testing DCCM of the experimental model is fit to the result of simulation of DCCM in Matlab. Consequently, the DCCM can substitute for other kinds of propellers especially in marine applications.
We investigate the feasibility of using an effective pulse control method to realize an almost exact state transmission through a uniform chain where the communication channel is immersed in a quantum environment. Thi...
详细信息
We investigate the feasibility of using an effective pulse control method to realize an almost exact state transmission through a uniform chain where the communication channel is immersed in a quantum environment. This pulse control is treated in a nonperturbative fashion, allowing for a more precise view. Using the non-Markovian quantum state diffusion equation, we calculate the dynamics of the transmission fidelity. The results show that the memory effects of the environment can support an effective transmission control that can be boosted under a non-Markovian environment. Our scheme provides another way to realize almost exact state transmission in a spin chain system.
In this paper, fast independent vector analysis (FastIVA) based on convolutional aliasing model is proposed to separate the aliased signals collected by distributed acoustic sensing (DAS) system, and the time-frequenc...
In this paper, fast independent vector analysis (FastIVA) based on convolutional aliasing model is proposed to separate the aliased signals collected by distributed acoustic sensing (DAS) system, and the time-frequency entropy is used to judge the separation performance. The results show that the time-frequency entropy interval of the separated signals and the source signals correspond to each other, which means that the aliased signals are separated. This method is used to improve the accuracy of DAS system signal detection and recognition in complex real environment, and reduce the number of false alarm events.
In this work a recently developed mathematical programming formulation called adaptation is compared with the widely used stochastic programming method in the context of electric infrastructure expansion planning. Alt...
详细信息
In this work a recently developed mathematical programming formulation called adaptation is compared with the widely used stochastic programming method in the context of electric infrastructure expansion planning. Although the structure of the adaptation method closely resembles that of a generic stochastic program it diverges from the temporal conventions of traditional electric infrastructure formulations. While traditional stochastic programming formulations restrict first and later stage capacity investments to separate time periods, the first and later stage capacity investments in adaptation overlap in time. Additionally, recourse decisions for all scenarios are defined relative to the central core trajectory in the same time period rather than the node at the previous time period in the stochastic programming scenario tree. After an in-depth discussion of stochastic programming and adaptations' formulations, a six bus simulation is provided to facilitate a more concrete comparison of the two methods. Uncertainties considered in the simulation include, wind and solar build costs, carbon taxes, demand and peak demand growth, natural gas fuel prices, and transmission costs.
Solving nonlinear equations is an important problem in engineering eld. Therefore, the study of ecient algorithm is of great signicance. Teaching-LearningBased Optimization (TLBO) has the advantages of simple algorith...
详细信息
暂无评论