An extremum-seeking control approach for constrained robotic motion tasks

Koropouli, Vasiliki; Gusrialdi, Azwirman; Hirche, Sandra; Lee, Dongheui

doi:10.1016/j.conengprac.2016.04.004

Cited by 11 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the above limitations and increasing volume of traffic every year; more flexible, robust, and computationally efficient approaches for controlling traffic networks of multiple controllers are necessary. In this context, RL [34,18,35] that has served different roles in automating and supporting knowledge-intensive tasks in different engineering fields such as civil [36,37], transportation [9,14,38,39], architecture [40], and control [41][42][43] can be beneficial. RL is a promising approach that provides traffic signal controllers with the ability of self-learning and can address the mentioned shortcomings.…”

Section: Related Workmentioning

confidence: 99%

Traffic signal optimization through discrete and continuous reinforcement learning with robustness analysis in downtown Tehran

Aslani

Seipel

Mesgari

et al. 2018

Advanced Engineering Informatics

View full text Add to dashboard Cite

Traffic signal control plays a pivotal role in reducing traffic congestion. Traffic signals cannot be adequately controlled with conventional methods due to the high variations and complexity in traffic environments. In recent years, reinforcement learning (RL) has shown great potential for traffic signal control because of its high adaptability, flexibility, and scalability. However, designing RL-embedded traffic signal controllers (RLTSCs) for traffic systems with a high degree of realism is faced with several challenges, among others system disturbances and large state-action spaces are considered in this research.The contribution of the present work is founded on three features: (a) evaluating the robustness of different RLTSCs against system disturbances including incidents, jaywalking, and sensor noise, (b) handling a highdimensional state-action space by both employing different continuous state RL algorithms and reducing the state-action space in order to improve the performance and learning speed of the system, and (c) presenting a detailed empirical study of traffic signals control of downtown Tehran through seven RL algorithms: discrete state Q-learning( ), SARSA( ), actor-critic( ), continuous state Q-learning( ), SARSA( ), actor-critic( ), and residual actor-critic( ).In this research, first a real-world microscopic traffic simulation of downtown Tehran is carried out, then four experiments are performed in order to find the best RLTSC with convincing robustness and strong performance. The results reveal that the RLTSC based on continuous state actor-critic( ) has the best performance. In addition, it is found that the best RLTSC leads to saving average travel time by 22% (at the presence of high system disturbances) when it is compared with an optimized fixed-time controller.

show abstract

Section: Related Workmentioning

confidence: 99%

Traffic signal optimization through discrete and continuous reinforcement learning with robustness analysis in downtown Tehran

Aslani

Seipel

Mesgari

et al. 2018

Advanced Engineering Informatics

View full text Add to dashboard Cite

show abstract

“…Extremum seeking control (ESC) has been consistently attracting research attention in the past two decades due to its ability to design a controller for the system at hand, while optimizing an unknown performance function. Therefore, it finds applications in many engineering fields, spanning from power optimization, 1 robotic motion control, 2 source seeking 3,4 . To date, various ESC methods have been proposed by, for example, incorporating dither signals and averaging methods, 5‐7 sliding mode control, 8,9 sample‐data optimization, 10,11 adaptation‐based methods, 12,13 and numerical optimization methods 14‐16 .…”

Section: Introductionmentioning

confidence: 99%

Numerical optimization‐based extremum seeking control of a class of constrained nonlinear systems via finite‐time state transition

Yuan

Fabiani

Baldi

2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article studies the extremum seeking control (ESC) problem for a class of constrained nonlinear systems. Specifically, we focus on a family of constraints that allows to reformulate the original nonlinear system in the so-called input-output normal form. To steer the system to optimize a performance function without knowing its explicit form, we propose a novel numerical optimization-based extremum seeking control (NOESC) design consisting of a constrained numerical optimization method and an inversion-based feedforward controller. In particular, a projected gradient descent algorithm is exploited to produce the state sequence to optimize the performance function, whereas a suitable boundary value problem accommodates the finite-time state transition between each two consecutive points of the state sequence. Compared to available NOESC methods, the proposed approach (i) can explicitly deal with output constraints; (ii) can consider a direct dependence on the states of the internal dynamics in the performance function; (iii) the internal dynamics do not have to be necessarily stable. The effectiveness of the proposed ESC scheme is shown through extensive numerical simulations and design of antilock braking systems.

show abstract

“…Hong and Li optimized ESC parameters using the particle swarm optimization (PSO) method, which guaranteed convergence [24]. These optimization methods and others aimed to decrease the convergence error and increase the speed of ESC for engineering applications [7,12,14,15,[25][26][27][28][29][30].…”

Section: Introductionmentioning

confidence: 99%

“…HE EXTREMUM SEEKING control (ESC) method aims to meet nonlinear performance criteria of a system using the adaptive control method. The ESC method has been used in a lot of engineering systems such as nuclear reactors [1,2], tracking the maximum power point of renewable energy systems [3][4][5], control of chemical systems [6][7][8], control of bioreactors [9][10][11][12][13], and mobile robots [14][15][16][17][18]. Because the ESC method has a lot of applications in the control of physical systems, researchers are interested in this control method.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Variable Order Extremum-Seeking Controller Design for Mobile Robots

Atan

2019

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

In this paper, a fuzzy variable order extremumseeking control (FVO-ESC) system for a mobile robot are designed. Fractional order controllers have advantages in the control of nonlinear systems such as a wider area of stability and performance enhancement in the presence of noise. The main proposal of the paper is to increase the performance of the fractional order controller. So, a variable order controller was designed for a mobile robot, and a fuzzy logic controller was designed according to user experiences to tune the controller order. The proposed FVO-ESC approach has been validated the effects on nonlinear systems such as the mobile robot system. It has been put forward in the preliminary investigation that the order of the fractional order ESC controller affects the overshoot and time to reach the target. The results suggested that a variable-level controller would have better performance. The results show that the proposed FVO-ESC control approach provides optimum performance for mobile robot systems.

show abstract

An extremum-seeking control approach for constrained robotic motion tasks

Cited by 11 publications

References 21 publications

Traffic signal optimization through discrete and continuous reinforcement learning with robustness analysis in downtown Tehran

Traffic signal optimization through discrete and continuous reinforcement learning with robustness analysis in downtown Tehran

Numerical optimization‐based extremum seeking control of a class of constrained nonlinear systems via finite‐time state transition

Fuzzy Variable Order Extremum-Seeking Controller Design for Mobile Robots

Contact Info

Product

Resources

About