Kinematic and Dynamic Adaptive Control of a Nonholonomic Mobile Robot using a RNN

Oubbati, Mohamed; Schanz, Michael; Levi, Paul

doi:10.1109/cira.2005.1554250

Cited by 20 publications

(23 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By replacing H kẑk+1 byf k +Ĝ k τ k , and employing the formulations in De nitions 3.5 and 3.12 to factorize completely the resulting expression in terms of τ k , it is possible to differentiate the cost function with respect to τ k and equate to zero, in order to get the dual control law (13). The resulting second order partial derivative of J inn with respect to τ k , the Hessian matrix, is given…”

Section: Remark 33mentioning

confidence: 99%

“…Pre-trained function estimators, typically arti cial neural networks (ANNs), have been used to render nonadaptive conventional controllers more robust in the face of uncertainty [12], [13]. These techniques require preliminary open-loop plant identi cation and remain blind to parametric and/or functional variations taking place after the training phase.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dual Adaptive Dynamic Control of Mobile Robots Using Neural Networks

Bugeja

Fabri

Camilleri

2009

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

This paper proposes two novel dual adaptive neural control schemes for the dynamic control of nonholonomic mobile robots. The two schemes are developed in discrete-time and the robot's nonlinear dynamic functions are assumed to be unknown. Gaussian radial basis function and sigmoidal multilayer perceptron neural networks are used for function approximation. In each scheme, the unknown network parameters are estimated stochastically in real-time, and no preliminary of ine neural network training is used. In contrast to other adaptive techniques hitherto proposed in the literature on mobile robots, the dual control laws presented in this paper do not rely on the heuristic certainty equivalence property but account for the uncertainty in the estimates. This results in a major improvement in tracking performance, despite the plant uncertainty and unmodelled dynamics. Monte Carlo simulation and statistical hypothesis testing are used to illustrate the effectiveness of the two proposed stochastic controllers as applied to the trajectory tracking problem of a differentially driven wheeled mobile robot.

show abstract

Section: Remark 33mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dual Adaptive Dynamic Control of Mobile Robots Using Neural Networks

Bugeja

Fabri

Camilleri

2009

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

show abstract

“…If we consider that these parameters are time varying, the problem becomes more complicated. To solve this problem, we designed an adaptive neurocontrol system with two levels [19]. In the first level, a recurrent neural network (ESN K ) improves the robustness of a kinematic controller and generates desired linear and angular velocities, necessary to track a reference trajectory.…”

Section: Adaptive Motion Control With Esnsmentioning

confidence: 99%

A neural framework for adaptive robot control

Oubbati

Palm

2009

Neural Comput & Applic

View full text Add to dashboard Cite

This paper investigates how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems such as motion control and behavior generation. We have designed an adaptive motion control approach based on a novel recurrent neural network, called Echo state networks. The advantage is that no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters in the robot. To generate the robot behavior over time, we adopted a biologically inspired approach called neural fields. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction, which navigates a mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles.

show abstract

“…First, this was carried out by Kanayama (Kanayama et al, 1990) through the using kinematic based backstepping controller. After his study, this controller has been used by other researchers (Fierro and Lewis, 1995;Oubbati, et al, 2005;Hwang, et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Differential Drive Mobile Robot Trajectory Tracking With Using Pid and Kinematic Based Backstepping Controller

Demirbaş¹,

Kalyoncu²

2017

Scitech

View full text Add to dashboard Cite

ABSTRACT:In this study, the mathematical model of a nonholonomic vehicle was derived. A PID and kinematic based backstepping controller (KBBC) was designed for a differential drive mobile robot to be able to track a desired trajectory. The KBBC was used to overcome the nonlinearity of the trajectory tracking and the PID controllers was used for the DC motors' speeds adjustments. Responses of the vehicle's controller in the square shaped trajectory had obtained and results were graphically presented. The effectiveness of the designed controller has been discussed.

show abstract

Kinematic and Dynamic Adaptive Control of a Nonholonomic Mobile Robot using a RNN

Cited by 20 publications

References 12 publications

Dual Adaptive Dynamic Control of Mobile Robots Using Neural Networks

Dual Adaptive Dynamic Control of Mobile Robots Using Neural Networks

A neural framework for adaptive robot control

Differential Drive Mobile Robot Trajectory Tracking With Using Pid and Kinematic Based Backstepping Controller

Contact Info

Product

Resources

About