In this paper a novel mechanism for acquiring shared symbols in multi-agent cooperative task is introduced. Inspired by human communication, a technique is suggested in which learning the behaviors and learning how to...
详细信息
ISBN:
(纸本)9781424448081
In this paper a novel mechanism for acquiring shared symbols in multi-agent cooperative task is introduced. Inspired by human communication, a technique is suggested in which learning the behaviors and learning how to communicate are decomposed. Decomposing the shared symbol acquisition into two separate learning phases not only simplifies the learning algorithm but also it speeds up the process. Moreover, utilizing the gained information about the environment in the behavior learning phase, agent communication is learned easily. A couple of simulations are conducted to support the idea. Simulation results show that agents could assign meaning to symbols and transfer information among themselves using the learned symbols. Roughly speaking, they could form a language.
This paper proposes a new methodology for analysis and design of robust fuzzy Takagi-Sugeno (TS) control, with PID structure, for nonlinear systems, based on gain and phase margins specifications. The nonlinear system...
详细信息
ISBN:
(纸本)9781424448081
This paper proposes a new methodology for analysis and design of robust fuzzy Takagi-Sugeno (TS) control, with PID structure, for nonlinear systems, based on gain and phase margins specifications. The nonlinear system to be controlled, is studied in the context of Linear Parameters Varying (LPV) systems, it is partitioned into several linear sub-models in terms of transfer function, forming a convex polytope. Once defined the linear sub-models of the plant, these are organized into fuzzy Takagi-Sugeno (TS) structure. From the Parallel Distributed Compensation (PDC) strategy, a mathematical formulation is defined in the frequency domain, based on the gain and phase margins specifications, to obtain robust PID sub-controllers in accordance to the Takagi-Sugeno fuzzy model of the plant. Results for the robust stability conditions with the proposal of one Axiom and two Theorems are also presented.
Particle filter (PF) is a method for discrete approximation of dynamic and non-Gaussian probability distribution by using numerous particles, and its procedure can execute at high speed and is suitable for on-line app...
详细信息
ISBN:
(纸本)9781424448081
Particle filter (PF) is a method for discrete approximation of dynamic and non-Gaussian probability distribution by using numerous particles, and its procedure can execute at high speed and is suitable for on-line applications. However, in conventional methods, a weighted average value or a maximum weighted value of particles is used as a filter output, and information on most particles is disregarded. On the other hand, an adaptive vector quantization (AVQ) algorithm called competitive reinitialization learning (CRL) that can achieve high-speed adaptation without depending on initial conditions has been proposed. Then, in this research, a method for extracting information on shape of probability density distributions by combining PF with CRL is proposed. Moreover, a rapid adaptation performance and the robustness of the proposed method are shown by the simulations.
Online coordination of visual information with slow speed manipulator control is studied in the specific task of three dimensional robotic catching using position based visual servoing. The problem involves the design...
详细信息
ISBN:
(纸本)9781424448081
Online coordination of visual information with slow speed manipulator control is studied in the specific task of three dimensional robotic catching using position based visual servoing. The problem involves the design and application of a recursive algorithm to extract and predict the position of an object in a 3D environment from one feature correspondence from a monocular image sequence. The measured data are the noisy image plane coordinates of object match taken from image in the sequence. Image plane noise levels are allowed and investigated. The target trajectory estimation is formulated as a tracking problem, which can use an arbitrary large number of images in a sequence and is done using Recursive Least Squares (RLS). The feasibility of our methods for catching are demonstrated by both simulations and experiments using a a real-time vision system and a six-degree-of-freedom robotic arm with speed capabilities of up to 1.0 m/s.
In this paper a study on rendering of environmental force feedback in mobile robot teleoperation based on fuzzy logic is presented. To ensure safety of mobile robot teleoperation it is often necessary to provide envir...
详细信息
ISBN:
(纸本)9781424448081
In this paper a study on rendering of environmental force feedback in mobile robot teleoperation based on fuzzy logic is presented. To ensure safety of mobile robot teleoperation it is often necessary to provide environmental force feedback which is related to the distance between the obstacles and the mobile robot. In previous approaches force feedback was rendered based on the measured distance between the obstacles and the mobile robot. In this work, a novel method for force feedback rendering using fuzzy logic is presented. In proposed approach derivative of the distance to the obstacle is used for defining the amount of environmental force feedback which is displayed to human-operator. Fuzzy rules and controller are designed and simulation results are shown. Advantages of the proposed approach are discussed.
The conventional Q-learning algorithm is described by a finite number of discretized states and discretized actions. When the system is represented in continuous domain, this may cause an abrupt transition of action a...
详细信息
ISBN:
(纸本)9781424448081
The conventional Q-learning algorithm is described by a finite number of discretized states and discretized actions. When the system is represented in continuous domain, this may cause an abrupt transition of action as the state rapidly changes. To avoid this abrupt transition of action, the learning system requires fine-tuned states. However, the learning time significantly increases and the system becomes computationally expensive as the number of states increases. To solve this problem, this paper proposes a novel Q-learning algorithm, which uses fuzzified states and weighted actions to update its state-action value. By applying the concept of fuzzy set to the states of Q-learning and using the weighted actions, the agent efficiently responds to the rapid changes of the states. The proposed algorithm is applied to omni-directional mobile robot and the results demonstrate the effectiveness of the proposed approach.
Proportional integral derivative (PID) controller tuning is an area of interest for researchers in many disciplines of science and engineering. This paper presents a new algorithm for PID controller tuning based on a ...
详细信息
ISBN:
(纸本)9781424448081
Proportional integral derivative (PID) controller tuning is an area of interest for researchers in many disciplines of science and engineering. This paper presents a new algorithm for PID controller tuning based on a combination of the foraging behavior of E coli bacteria foraging and Particle Swarm Optimization (PSO). The E colt algorithm depends on random search directions which may lead to delay in reaching the global solution. The PSO algorithm may lead to possible entrapment in local minimum solutions. This paper proposed a new algorithm Bacteria Foraging oriented by PSO (BF-PSO). The new algorithm is proposed to combines both algorithms' advantages in order to get better optimization values. The proposed algorithm is applied to the problem of PID controller tuning and is compared with conveniently Bacterial Foraging algorithm and Particle swarm optimization.
As a specialisation of Ho ionic agent-based distributed manufacturing control, intelligent product-driven manufacturing control paradigm has recently emerged as one of the most promising paradigms for the development ...
详细信息
ISBN:
(纸本)9781424442201
As a specialisation of Ho ionic agent-based distributed manufacturing control, intelligent product-driven manufacturing control paradigm has recently emerged as one of the most promising paradigms for the development of next generation manufacturing intelligent control systems. But major issue to be solved to make this paradigm effective in real world industrial environment is related to the lack of efficiency of agent-based local decision-making approaches employed. The research work presented in this paper focuses on this pending issue and proposes and formalizes the combination of main capabilities of agent-based intelligent product-driven manufacturing control paradigm and computationalintelligence genetic algorithm optimisation tool for the development of effective and efficient intelligent product driven agent-based distributed dynamic scheduling and control strategy. This challenging combination is achieved by neural network-based machine learning technique and enables enhancing manufacturing system reactivity, flexibility and fault tolerance, as well as maintaining behavioural stability and optimality.
Nowadays, magneto-rheological (MR) fluid dampers (MRD) are widely used for the semi-active suspension control in vibration community. However, the inherent nonlinear nature of the MRD causes challenges for damping con...
详细信息
ISBN:
(纸本)9781424448081
Nowadays, magneto-rheological (MR) fluid dampers (MRD) are widely used for the semi-active suspension control in vibration community. However, the inherent nonlinear nature of the MRD causes challenges for damping control of the suspension system using this device with high performance. Therefore, the development of an accurate modeling method for a MRD is necessary to take advantage of its unique characteristics. This paper focuses on the development of a nonlinear black box model to identify and verify behaviors of a MR damper. The model is built by using an online self tuning fuzzy (OSTF) method based on neural technique. The behavior of the MRD is directly estimated through the box. A series of experiments and modeling analysis had been done on test rigs to validate the effectiveness of the design nonlinear black box in predicting the damping force.
The paper presents a comparison between several modern control solutions for mechatronic systems. A synthesis of the structures included in the modern based-design solutions is presented. They deal with model predicti...
详细信息
The paper presents a comparison between several modern control solutions for mechatronic systems. A synthesis of the structures included in the modern based-design solutions is presented. They deal with model predictive control, fuzzy control, adaptive control and combination between different strategies and control structures. Digital simulation results are based on step and rectangular modifications of the reference input.
暂无评论