A review of statistical models for global optimization

Žilinskas, Antanas

doi:10.1007/bf00122051

Cited by 63 publications

(22 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complex power spectrum is possible to obtain by dividing the energy spectrum with the integration time t. The integrated relations are the Fourier transform expressions and can be calculated by FFT algorithm [21][22][23][24][25][26][27][28].…”

Section: Optimization Of the Dynamic Behaviormentioning

confidence: 99%

Assisted Methods for Optimization in Robotics

Olaru¹,

Hajduk²,

Olaru³

et al. 2017

IJMO

View full text Add to dashboard Cite

Abstract-Optimization of the elements and systems from Robotics is one of the most complicated problem with the final goal to obtain the end-effecters' 3D extreme space precision trajectory. In the paper are shown some of the proper methods for optimization in Robotics: optimal Extenics choose of the precision-stability working point of one linear hydraulic cylinder; modelling and optimization of the DC electrical drive of the robots; optimising the dynamic behaviour of the robots by using the intelligent dampers; optimise the inverse kinematics results by using one complex proper method; optimise the multi robots application by using the algorithm to choose the optimal application points of the robots' bases and by construct the parallel robot structure using three arm type robots. All applied method solves one small part of the complex problems of the optimisation in robotics.Index Terms-Assisted optimization LabVIEW methods, forward kinematics, inverse kinematics, dynamic behavior, 3D space trajectory.

show abstract

Section: Optimization Of the Dynamic Behaviormentioning

confidence: 99%

Assisted Methods for Optimization in Robotics

Olaru¹,

Hajduk²,

Olaru³

et al. 2017

IJMO

View full text Add to dashboard Cite

show abstract

“…In the last decades, extensive research has been made within the field of estimating parameters of deterministic and stochastic systems, respectively [6][7][8][9][10][11][12][13]. Most attention has been drawn to local and global nonlinear optimization methods.…”

Section: B Previous Workmentioning

confidence: 99%

Dynamic system classifier

et al. 2016

View full text Add to dashboard Cite

Stochastic differential equations describe well many physical, biological and sociological systems, despite the simplification often made in their derivation. Here the usage of simple stochastic differential equations to characterize and classify complex dynamical systems is proposed within a Bayesian framework. To this end, we develop a dynamic system classifier (DSC). The DSC first abstracts training data of a system in terms of time dependent coefficients of the descriptive stochastic differential equation. Thereby the DSC identifies unique correlation structures within the training data. For definiteness we restrict the presentation of DSC to oscillation processes with a time dependent frequency ω(t) and damping factor γ(t). Although real systems might be more complex, this simple oscillator captures many characteristic features. The ω and γ timelines represent the abstract system characterization and permit the construction of efficient signal classifiers. Numerical experiments show that such classifiers perform well even in the low signal-to-noise regime.

show abstract

“…These include sampling at an upper confidence bound of the predicted function [9], [10], using the probability of improvement [11], [12], and the use of expected improvement [13], [14]. The latter has shown to effectively trade off exploration of the parameter space and exploitation of the known good areas, without requiring algorithm parameters to be carefully tuned.…”

Section: Related Workmentioning

confidence: 99%

Adapting control policies for expensive systems to changing environments

Tesch

Schneider

Choset

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-Many controlled systems must operate over a range of external conditions. In this paper, we focus on the problem of learning a policy to adapt a system's controller based on the value of these external conditions in order to always perform well (i.e., maximize system output). In addition, we are concerned with systems for which it is expensive to run experiments, and therefore restrict the number that can be run during training. We formally define the problem setup and the notion of an optimal control policy. We propose two algorithms which aim to find such a policy while minimizing the number of system output evaluations. We present results comparing these algorithms and various other approaches and discuss the inherent tradeoffs in the proposed algorithms. Finally, we use these methods to train both simulated and physical snake robots to automatically adapt to changing terrain, and demonstrate improved performance on test courses with changing environments.

show abstract

A review of statistical models for global optimization

Cited by 63 publications

References 6 publications

Assisted Methods for Optimization in Robotics

Assisted Methods for Optimization in Robotics

Dynamic system classifier

Adapting control policies for expensive systems to changing environments

Contact Info

Product

Resources

About