Adaptive Control for Uncertain Model of Omni-directional Mobile Robot Based on Radial Basis Function Neural Network

Kim, Duyen Ha Thi; Manh, Tien Ngo; Mạnh, Cường Nguyễn; Nguyen, Nhan Duc; Tien, Dung Pham; Van, Manh Tran; Xuan, Minh Phan

doi:10.1007/s12555-019-1004-6

Cited by 11 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training specimens of radial basis probabilistic neural network (RBPNN) can fully consider the influence of different modes [ 21 ]. The model structure can be divided into input layer, first hidden layer, second hidden layer and output layer, respectively [ 22 ]. x is an n -dimensional input sample, and the transmission function of the first hidden node is K .…”

Section: Radial Basis Function (Rbf) Neural Networkmentioning

confidence: 99%

Clustering Analysis Algorithm of Volleyball Simulation Based on Radial Fuzzy Neural Network

Yan

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Aiming at a series of problems existing in volleyball, based on radial fuzzy neural network theory, the optimized simulation clustering analysis algorithm is used to monitor and analyze volleyball. By analyzing the feature weights of nodes at different stages, the optimal radial fuzzy neural network was constructed, which was combined with the simulation clustering algorithm to obtain the relevant optimization model describing volleyball. The accuracy of the optimization model is verified by comparing with the original model. The results show that with the increase of response, the response curves of different algorithms show fluctuation. Among them, the fluctuation range of MPDR (minimum power distortionless response) algorithm is larger, and the value of the curve obtained by MVDR (minimum variance distortionless response) algorithm differs greatly from that of the optimization algorithm at some key nodes, while the beam changing chart obtained by the optimization algorithm can better reflect the changing trend of the beam. Model indexes under different algorithms are different. When the number of iterative steps is less than 30, indexes under different algorithms are all greater than the standard value. When the number of iterations is more than 30, the indexes under different algorithms are all less than the standard value. Through verification, it can be seen that the original model can only describe the first stage of volleyball, while the optimization model can describe the whole process of volleyball. It shows that the optimization model can be used to describe and analyze volleyball-related data. And the algorithm can be used to better predict and analyze volleyball, and the analysis results can provide relevant guidance for volleyball. The optimization model provides basis and theoretical support for the application of volleyball simulation clustering algorithm, so as to better promote volleyball and better guide the movement.

show abstract

Section: Radial Basis Function (Rbf) Neural Networkmentioning

confidence: 99%

Clustering Analysis Algorithm of Volleyball Simulation Based on Radial Fuzzy Neural Network

Yan

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Derive from Lemma 1, Assumption 1 and 2 and the control signals obtained in (49), we attain the following equation…”

Section: Model-free-based Fractional-order Sliding Surface Integrated...mentioning

confidence: 99%

“…q , e 𝜔 u I q , e 𝜔 1 I q , … , e T i I q , e 𝜔 i I q , … , e T n+1 I q , {e 𝜔 r I q ) ∈ R q(2n+3)×q(2n+3) , For the control signals defined in (49), under Assumptions 1 and 2, the adaptation law expressed in (50), and associated with Theorem 1 render the nonlinear R2R system given in (22) semi-global stable in the absence of system dynamics f and g.…”

Section: Model-free-based Fractional-order Sliding Surface Integrated...mentioning

confidence: 99%

“…The research carried out associated RBFNN and Fuzzy Logic with designing an adaptive controller based on the DSC approach to ensure high precision of robot movement under the serious effects of disturbances. 49 Inspired from the analysis of previous studies mentioned above, in this article, we pay attention to developing a generalized model, a hierarchical anti-imprecision control scheme with a Fractional-order Sliding Surface controller, and an approximation algorithm for R2R systems in order to achieve high control accuracy and robustness. The three main contributions of this study can be expressed as follows:…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Model‐free hierarchical control with fractional‐order sliding surface for multisection web machines

Dang

Nguyen

Tran

et al. 2022

Adaptive Control & Signal

View full text Add to dashboard Cite

Due to the nonlinearities and dynamical properties of multisection web machines, it is essential to accomplish an appropriate mathematical model as well as design a compatible control scheme. A generalized fully driven web winding model is constructed taking unpredictable changes of moment of inertia and radius of rolls into consideration. In this article, a fractional‐order sliding surface algorithm‐based hierarchical control frame is applied to multisection web machines to deal with matched and mismatched uncertainties and disturbances. In addition, the Radius Basis Function neural network is deployed to estimate necessary system dynamics and the proposed control scheme taking advantage of first‐order low‐pass filters to produce virtual control signals without complicated calculation and attenuate the explosion of terms phenomenon. Finally, the semi‐global stability of the entire system is determined using Lyapunov's stability theory. The simulation results are presented to clarify the superior performance of robust control algorithm and approximation law in the presence of nonideal elements.

show abstract

“…The robot keeps updating its location in a map whenever it manoeuvres on the ground so that the end point of the robot is attained efficiently. Once the robot positioning is done, the robot can track the object and plans multiple paths to reach its target and thus the autonomous navigation of the robot is performed [11].…”

Section: Fig 1 Annual Procurement Of Industrial Robots In the Thousandsmentioning

confidence: 99%

Design of Ball Collecting Robot

Jánoš

Murali

2021

TST

View full text Add to dashboard Cite

A concept of four-wheeled mobile service robot capable of collecting balls from the Tennis court is proposed in this article. The robot is capable of manoeuvring on its own in an autonomous way and also it can be operated wirelessly. The robot is built using the Arduino Uno R3 microcontroller board along with sensors like LiDAR, ultrasound sensor, optical encoders, infrared sensor, camera for vision system. Sensor fusion can be implemented for localization of the robot while detection of the tennis ball can be attained by learning based object detection algorithm using OpenCV. A* algorithm is proposed for the navigation of the robot towards the object. Wireless operation of the robot can be achieved with the Bluetooth technology using the Android application via a smartphone. The article is an overview and information.

show abstract

Adaptive Control for Uncertain Model of Omni-directional Mobile Robot Based on Radial Basis Function Neural Network

Cited by 11 publications

References 27 publications

Clustering Analysis Algorithm of Volleyball Simulation Based on Radial Fuzzy Neural Network

Clustering Analysis Algorithm of Volleyball Simulation Based on Radial Fuzzy Neural Network

Model‐free hierarchical control with fractional‐order sliding surface for multisection web machines

Design of Ball Collecting Robot

Contact Info

Product

Resources

About