A distributed approach to reinforcement learning in tasks of ramp metering and dynamic route guidance is presented. The problem domain, a freeway integration control application, is formulated as a distributed reinfor...
详细信息
A distributed approach to reinforcement learning in tasks of ramp metering and dynamic route guidance is presented. The problem domain, a freeway integration control application, is formulated as a distributed reinforcement learning problem. The DRL approach was implemented via a multi-agent control architecture where the decision agent was assigned to each of the on-ramp or VMS. The return of each agent is simultaneously updating a single shared policy. The control strategypsilas efficiency is demonstrated through its application to the simple freeway network. Analyses of simulation results using this approach show significant improvement over traditional local control, especially for the case of large traffic demand. Using the DRL approach, the TTS of the Network has been reduced by 20% under the heavy demands.
In this paper, we theoretically analyze the limitation of the Quotient Image (QI) method proposed by Shashua and present a new way to compute the quotient image. Based on the observation that nine basis point light so...
详细信息
In this paper, we theoretically analyze the limitation of the Quotient Image (QI) method proposed by Shashua and present a new way to compute the quotient image. Based on the observation that nine basis point light sources can represent almost arbitrary lighting conditions for face recognition application, we use the corresponding nine basis images which are all real images to span the image space. And similar to the QI, our method can not only get an illumination invariant image but also synthesize a new image under arbitrary illumination conditions. We provide an experimental result to show the effectiveness of our algorithm as well.
A two-loop cascade adaptive controller is proposed for a non-stable, non-linear, strong coupling system using backstepping and fuzzy neural network. The proposed approach uses fuzzy neural networks to approximate unkn...
详细信息
A two-loop cascade adaptive controller is proposed for a non-stable, non-linear, strong coupling system using backstepping and fuzzy neural network. The proposed approach uses fuzzy neural networks to approximate unknown nonlinear function. Then, use backstepping to design adaptive controller to realize self-balancing control of robot. The simulation results indicate that both speediness and stability performance in robot is improved, and there is well control performance in trouble.
The present book includes a set of selected papers from the 5th "internationalconference on informatics in control automation and robotics" (ICINCO 2008), held in Funchal-Madeira, Portugal, 11-15 May 2008. ...
详细信息
ISBN:
(数字)9783642002717
ISBN:
(纸本)9783642002700
The present book includes a set of selected papers from the 5th "internationalconference on informatics in control automation and robotics" (ICINCO 2008), held in Funchal-Madeira, Portugal, 11-15 May 2008. The conference was organized in three simultaneous tracks: "Intelligent control Systems and Optimization", "robotics and automation" and "Systems Modeling, Signal Processing and control". The book is based on the same structure. The purpose of this conference is to bring together researchers, engineers and practitioners interested in the application of informatics to control, automation and robotics. informatics applications are pervasive in many areas of control, automation and robotics, and this conference intends to emphasize this connection, therefore, most papers highlight applications of Information Technology (IT) in these areas and present ideas on how to solve problems using IT, both in R&D and industrial applications. A diversity of papers are included in the book, ranging from papers describing advanced prototypes, systems, tools and techniques to papers presenting surveys indicating future directions.
A global terminal adaptive controller is designed for the modified Chuapsilas circuits with input uncertainties and unknown parameters, and the synchronization is achieved in finite time by adopting the concept of glo...
详细信息
A global terminal adaptive controller is designed for the modified Chuapsilas circuits with input uncertainties and unknown parameters, and the synchronization is achieved in finite time by adopting the concept of global terminal control. It can be concluded that the synchronization can achieved successfully with the assumption that the sign of uncertain parameter of input is known. And the parameters can be estimated accurately when the number of parameters satisfies some conditions, otherwise the synchronization can achieved but the parameters canpsilat be estimated effectively. At last, the numerical simulation shows the effectiveness of this proposed method and the conclusions.
This paper presents the design of lateral/directional control with RCS on reentry of reusable launch vehicle. The control law are designed, with great computational advantage,for a linear system and then applied in a ...
详细信息
This paper presents the design of lateral/directional control with RCS on reentry of reusable launch vehicle. The control law are designed, with great computational advantage,for a linear system and then applied in a nonlinear way with on-off type RCS. The lateral/directional control concept essentially reverses the traditional role of the lateral force effectors. The feedback of roll rate to aileron is used to damping the Dutch roll while the yaw jets is used to damping roll mode and maintaining the roll attitude. And a revised PWM is developed based on principle of equivalent accumulated impulse. The final simulation result shows the validity of this method.
Coal gas drainage out of the mine excavation workspace is the urgent problem to be solved for safe production, a novel double mode fuzzy control strategy of gas drainage system for the coal local ventilator is propose...
详细信息
Coal gas drainage out of the mine excavation workspace is the urgent problem to be solved for safe production, a novel double mode fuzzy control strategy of gas drainage system for the coal local ventilator is proposed in the paper. One fuzzy control mode is used in normal aeration state. The other mode is adopted to expel the gas from the mine well, when the gas strength is abnormal. The switching condition of the two modes is discussed, the air flow press distribution in digging laneway is analyzed, and the fuzzy control system is designed. The theory analysis and experiment results show that the suggested double mode fuzzy control schemes are transferred smoothly and the speed of local ventilator is adjusted according to the gas variable concentration in both the normal aeration and abnormal ventilation state, which assures the safety of coal mining.
This paper is concerned with the stabilization for linear neutral systems with distributed delays. Based on the model transformation of neutral type, the Lyapunov-Krasovskii functional method is employed to establish ...
详细信息
This paper is concerned with the stabilization for linear neutral systems with distributed delays. Based on the model transformation of neutral type, the Lyapunov-Krasovskii functional method is employed to establish the delay-dependent stability criterion. Through the controller parameterization and matrix transformation techniques, the desired parameters are solved from the delay-dependent design condition in terms of linear matrix inequalities, and the desired controller is explicitly formulated. Numerical example is given to illustrate the correctness of the proposed method.
A centralized multisensor unscented joint probabilistic data association algorithm, CMSUJPDA, is proposed for the multisensor multitarget tracking problem of the nonlinear system in clutter. In the algorithm, UKF is u...
详细信息
A centralized multisensor unscented joint probabilistic data association algorithm, CMSUJPDA, is proposed for the multisensor multitarget tracking problem of the nonlinear system in clutter. In the algorithm, UKF is used for the propagation of state distribution in the nonlinear system at first. Then the association of measurements to track is implemented according to the method of JPDA. Based on this, the CMSUJPDA algorithm is derived by use of the idea of sequential MSJPDA. Due to higher order of accuracy of UKF than EKF, the association probabilities and state estimates in our algorithm are not affected by the linearization error. Hence compared with MSJPDA/EKF, the accuracy and robustness of CMSUJPDA are more favorable. Finally simulation results show the superiority of the proposed algorithm.
The train control center which plays a central role of message communication is a pivotal sub-system of the china train control system. On the basis of developing and debugging the engineering prototype of the train c...
详细信息
The train control center which plays a central role of message communication is a pivotal sub-system of the china train control system. On the basis of developing and debugging the engineering prototype of the train control center, an index system for evaluating the safety of the train control center was set up. Based on the analytic hierarchy process, a safety evaluation method for the train control center was proposed. Using the technology of verification, validation and accreditation, comprehensive analysis to the safety evaluation index of the train control center was carried on. At last, the safety evaluation index of the whole train control center was obtained, which is useful to the nationalized train control center.
暂无评论