A Study of Effective Prediction Methods of the State-Action Pair for Robot Control Using Online SVR

2015 ◽  
Vol 27 (5) ◽  
pp. 469-479 ◽  
Author(s):  
Masashi Sugimoto ◽  
◽  
Kentarou Kurashige
Keyword(s):  
Linear Quadratic Regulator ◽  
The State ◽  
Support Vector ◽  
Linear Quadratic ◽  
Appropriate Behavior ◽  
State Action ◽  
Inverted Pendulum Model ◽  
Future State ◽  
Course Of Action ◽  
The Future

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270005/02.jpg"" width=""300"" /> Prediction of future state and action</div> In order to work effectively, a robot should be able to adapt to different environments by deciding its correct course of action according to the situation, using determinants other than pre-registered commands. For this purpose, the ability to predict the future state of a robot would be effective. On the other hand, the future state of a robot varies infinitely if it depends on its current action. Therefore, it is difficult to predict only the future state. Thus, it is important to simultaneously predict the state and the action that the robot will adopt. The purpose of this study was to investigate the prediction of the advanced future state and action of a robot. In this paper, the results of the study are reported and methods that allow a robot to decide its appropriate behavior quickly, according to the predicted future state are discussed. As an application example for evaluating the proposed method, the inverted pendulum model is used and the prediction results are compared with the robot’s actual responses. Then, two methods will be discussed for predicting the robot’s state and action. To perform state and action prediction, two methods are used, firstly the Online SVR (Support Vector Regression) and secondly Online SVR and the LQR (Linear Quadratic Regulator). </span>

Enterprise and Technology Architectures

2011 ◽  
pp. 167-221
Author(s):  
Eng K. Chew ◽  
Petter Gottschalk
Keyword(s):  
Business Strategy ◽  
Enterprise Architecture ◽  
Strategic Alignment ◽  
The State ◽  
State Change ◽  
It Strategy ◽  
Investment Portfolio ◽  
Future State ◽  
The Future

The role of integrated enterprise architecture in IT strategy and strategic alignment is explained in Chapter V. This chapter describes in detail the principles and methods for developing a business-aligned enterprise architecture that will define the roadmap to attain the future state of the enterprise envisioned by the business strategy and guide the IT investment portfolio necessary for the state change.

scholarly journals Direct Surge Margin Control for Aeroengines Based on Improved SVR Machine and LQR Method

2013 ◽  
Vol 2013 ◽  
pp. 1-17 ◽  
Author(s):  
Haibo Zhang ◽  
Fengyong Sun
Keyword(s):  
Support Vector Regression ◽  
Stability Margin ◽  
Linear Quadratic Regulator ◽  
Least Square ◽  
Support Vector ◽  
Linear Quadratic ◽  
Inlet Distortion ◽  
Surge Margin ◽  
Engine Stability ◽  
Margin Control

A novel scheme of high stability engine control (HISTEC) on the basis of an improved linear quadratic regulator (ILQR), called direct surge margin control, is derived for super-maneuver flights. Direct surge margin control, which is different from conventional control scheme, puts surge margin into the engine closed-loop system and takes surge margin as controlled variable directly. In this way, direct surge margin control can exploit potential performance of engine more effectively with a decrease of engine stability margin which usually happened in super-maneuver flights. For conquering the difficulty that aeroengine surge margin is undetectable, an approach based on improved support vector regression (SVR) machine is proposed to construct a surge margin prediction model. The surge margin modeling contains two parts: a baseline model under no inlet distortion states and the calculation for surge margin loss under supermaneuvering flight conditions. The previous one is developed using neural network method, the inputs of which are selected by a weighted feature selection algorithm. Considering the hysteresis between pilot input and angle of attack output, an online scrolling window least square support vector regression (LSSVR) method is employed to firstly estimate inlet distortion index and further compute surge margin loss via some empirical look-up tables.

scholarly journals Partizanų nepriklausomos Lietuvos valstybės vizija

2020 ◽  
Vol 2020/1 ◽  
pp. 141-163
Author(s):  
Mindaugas Pocius
Keyword(s):  
Social Justice ◽  
Social Exclusion ◽  
Economic Model ◽  
Political Thought ◽  
State Regulation ◽  
The State ◽  
Future State ◽  
The Future ◽  
Freedom Fighters ◽  
The Republic

The research, which is based on the documents of the anti-Soviet resistance of 1944–1953, makes an attempt at reconstructing the freedom fighters’ vision of independent Lithuania and analyses the image of the planned (projected) political and socio-economic model of the state, its underlying elements and principles, the evolution and context of the partisans’ political thought. Reflecting on inter-war Lithuania, life therein, resistance against the Soviets and the fierce struggle and sufferings of that time, the partisans sacredly believed in the restoration of independence and had a clear vision of the future state. The critical attitude of those who participated in the resistance towards Lithuania’s statehood had a great impact on the underlying elements of the said vision. In the partisans’ experience and understanding, social exclusion and public distrust of government institutions were among the most acute problems of the Republic of Lithuania which, in their conviction, caused the catastrophic crisis of the state and the society that resulted in the loss of independence in 1940. Leaders of the underground movement were fully aware of the ills and failures of the past and thus constructed an ideal, a dream of a comprehensively stronger and affluent state, democratic regime and fairer governance of the country. The partisans’ vision of a modern independent Lithuanian state was developed under the influence of the political thought of the rural intelligentsia, thus reflecting the outlook of an ordinary peasant farmer and akin attitudes of rural intellectuals. Realising that Lithuania existed on the divide between the Western and Eastern civilizations, partisan leaders made every attempt to emphasize their western identity and mentality, identified and positioned themselves as the outpost of Western civilization and European culture. Participants of the resistance movement followed basically social democratic, Christian ideals and values and sought to restore a modern democratic parliamentary republic free of social exclusion where social justice and solidarity would be the predominant components of state regulation. In summary, it can be stated that the present-day socio-economic model of the Nordic welfare state (that of Denmark, Norway, Sweden or Finland), which in its core is rather socialistic, is for the most part in line with the freedom fighters’ vision of the future state and was considered by them the most acceptable. Although present-day Lithuania does not fully satisfy their vision, Lithuanian resistance fighters expressed the eternal strive of people and nations for freedom, material and spiritual wellbeing and social justice.

scholarly journals Design of Linear Quadratic Regulator (LQR) Based on Genetic Algorithm for Inverted Pendulum

MENDEL ◽  
2017 ◽  
Vol 23 (1) ◽  
pp. 149-156
Author(s):  
Tomas Marada ◽  
Radomil Matousek ◽  
Daniel Zuth
Keyword(s):  
Genetic Algorithm ◽  
Control Problem ◽  
Inverted Pendulum ◽  
Linear Quadratic Regulator ◽  
Linear Quadratic ◽  
Optimal Response ◽  
Inverted Pendulum Model ◽  
Horizontal Path ◽  
Automatic Control Theory ◽  
Pendulum Model

One of the crucial problems in the dynamics and automatic control theory is balancing of an invertedpendulum robot by moving a cart along a horizontal path. This task is often used as a benchmark for di erentmethod comparison. In the practical use of the LQR method, the key problem is how to choose weight matricesQ and R correctly. To obtain satisfying results the experiments should be repeated many times with di erentparameters of weight matrices. These LQR parameters can be tuned by a Genetic Algorithm (GA) techniquefor getting better results. In our paper, the LQR parameters weight matrices Q and R which were tuned usingthe Genetic Algorithm. The simulations of the control problem are designed using MATLAB script code andMATLAB Simulink on an inverted pendulum model. The results show that the Genetic Algorithm is suitablefor tuning the parameters to give an optimal response. The control problem of the inverted pendulum was solvedsuccessfully.

scholarly journals Performance Evaluation of Pole Placement and Linear Quadratic Regulator Strategies Designed for Mass-Spring-Damper System Based on Simulated Annealing and Ant Colony Optimization

2021 ◽  
Vol 27 (11) ◽  
pp. 15-31
Author(s):  
Huthaifa Al-Khazraji ◽  
Luay T. Rasheed
Keyword(s):  
Performance Evaluation ◽  
Simulated Annealing ◽  
State Feedback ◽  
Linear Quadratic Regulator ◽  
The State ◽  
Ant Colony ◽  
System Stability ◽  
Pole Placement ◽  
Linear Quadratic ◽  
Mass Spring

This paper investigates the performance evaluation of two state feedback controllers, Pole Placement (PP) and Linear Quadratic Regulator (LQR). The two controllers are designed for a Mass-Spring-Damper (MSD) system found in numerous applications to stabilize the MSD system performance and minimize the position tracking error of the system output. The state space model of the MSD system is first developed. Then, two meta-heuristic optimizations, Simulated Annealing (SA) optimization and Ant Colony (AC) optimization are utilized to optimize feedback gains matrix K of the PP and the weighting matrices Q and R of the LQR to make the MSD system reach stabilization and reduce the oscillation of the response. The Matlab software has been used for simulations and performance analysis. The results show the superiority of the state feedback based on the LQR controller in improving the system stability, reducing settling time, and reducing maximum overshoot. Furthermore, AC optimization shows significant advantages for optimizing the parameters of PP and LQR and reducing the fitness value in comparison with SA optimization

Design and Performance Analysis of LQR Controller for Stabilizing Double Inverted Pendulum System

2017 ◽  
Vol 2 (9) ◽  
pp. 1-5
Author(s):  
Ghassan A. Sultan ◽  
Ziyad K. Farej
Keyword(s):  
Inverted Pendulum ◽  
Linear Quadratic Regulator ◽  
Linear Quadratic ◽  
Pendulum System ◽  
Inverted Pendulum Model ◽  
Inverted Pendulum System ◽  
Pendulum Model ◽  
Lqr Controller ◽  
And Performance ◽  
Performance Results

Double inverted pendulum (DIP) is a nonlinear, multivariable and unstable system. The inverted pendulum which continually moves toward an uncontrolled state represents a challenging control problem. The problem is to balance the pendulum vertically upward on a mobile platform that can move in only two directions (left or right) when it is offset from zero stat. The aim is to determine the control strategy that deliver better performance with respect to pendulum's angles and cart's position. A Linear-Quadratic-Regulator (LQR) technique for controlling the linearized system of double inverted pendulum model is presented. Simulation studies conducted in MATLAB environment show that the LQR controller are capable of controlling the multi output double inverted pendulum system. Also better performance results are obtained for controlling heavy driven part DIP system.

scholarly journals Map reduce technique for parallel-automata analysis of large scale rainfall data

2018 ◽  
Vol 7 (4) ◽  
pp. 2752 ◽  
Author(s):  
Tulasi Sunitha Manepalli ◽  
Dr. Chamakuzhi Subramanian
Keyword(s):  
Logistic Regression ◽  
Big Data ◽  
Large Scale ◽  
Rainfall Data ◽  
Rate Coefficients ◽  
Map Reduce ◽  
Support Vector ◽  
Mean Square ◽  
Course Of Action ◽  
The Future

Vast scale rainfall information assumes an imperative part in farming field thus early expectation of rainfall is important for the better finan-cial development of a nation. Rainfall expectation is an expert among the most troublesome issue far and wide in a year back. This data is generally secured in the unstructured course of action. Along these, tremendous measure of data has been accumulated and archived. Thus, storage and handling of such tremendous information for accurate rainfall forecast are a major test. Big Data innovation like Hadoop have developed to fathom the difficulties and issues of huge information utilizing distributed computing. Till date few examinations have been accounted for on the preparing of vast scale rainfall information utilizing MapReduce. In this paper, the huge scale rainfall information is anticipated by utilizing MapReduce system which plays out the capacities which are required and diminishes the task to get proficient ar-rangements through taking the information and isolating into smaller tasks. At that point, the three Regression Automata (RA) algorithms such as Linear Regression automata, Support Vector Regression Automata and Logistic Regression Automata. are utilized to forecast the future esteem of large scale rainfall data. The proposed framework serves as a tool that takes in the rainfall information from diminished information as input and predicts the future rainfall. The outcomes obviously demonstrate that the all the three RA models can anticipate the rainfall productively in different terms, such as, error rate, coefficients and mean square error.  

scholarly journals Crown Liability in Tort in New Zealand

2021 ◽  
Author(s):  
◽  
Daniel Paul Neazor
Keyword(s):  
New Zealand ◽  
Adverse Effects ◽  
The State ◽  
The Other ◽  
State Action ◽  
Business Opportunity ◽  
Other Hand ◽  
The Future ◽  
Individual Citizen ◽  
The Individual

<p>Direct review by the Courts (e. g . by prerogative writs) of Executive acts and decisions generally provides the individual citizen with a means of overcoming for the future the adverse effects of such decisions and actions, but it does not provide any means of compensating him for detriments to his interests already caused . Such detriments will generally be those which have accrued in full by the time the decision is reviewed but may in some cases be of a continuing nature, e. g . where, because of refusal of a licence, a business opportunity is lost. Tort actions against the State on the other hand, will allow the Courts not only to examine the actions of State servants, and determine whether they conform with the Courts' view of the proper behaviour of officials but also, and principally, to compensate the individual citizen whose interests have been affected by State action. Such actions may thus furnish an indirect means of control of the Executive as well as a means of compensation for injury.</p>

Sign in / Sign up

Export Citation Format

Share Document