An artificial neural network based dynamic controller for a robot in a multi-agent system

Jolly, K. G.; Kumar, Rahul; Vijayakumar, R.

doi:10.1016/j.neucom.2009.08.011

Cited by 17 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two control performances were implemented and tested using Matlab Simulink models: A. Artificial NN controller (Jolly, Kumar, & Vijayakumar, 2009) under slippage; B. Adaptive NN controller with slip-compensation under slippage. We adopt vehicle parameters (Figure 1) as follows: m = 5 kg, I = 4 kgm 2 , L = 0.2 m, r = 0.15 m, under the time varying external disturbance τ d = (sin t, cos t, 1) T N, v r = 1 m/s, ω r = 1/3rad/s.…”

Section: Simulation Resultsmentioning

confidence: 99%

“…But, it is difficult to obtain an accurate mathematical model for applying computed torque controllers or other model-based controllers in practice. Following the neural network (NN) development, the neural network-based control of mobile robots has been the subject of intense research in recent years (Fierro & Lewis, 1998;Jolly, Kumar, & Vijayakumar, 2009;Sun, Pei, Pan, & Zhang, 2013;Wang, Ge, Lee, & Lai, 2006). These researches had produced new methods for solving the main difficulties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive motion control of wheeled mobile robot with unknown slippage

Gao

Song

Ding

et al. 2014

International Journal of Control

View full text Add to dashboard Cite

As a major representative nonholonomic system, wheeled mobile robot (WMR) is often used to travel across off-road environments that could be unstructured environments. Slippage often occurs when WMR moves in slopes or uneven terrain, and the slippage generates large accumulated position errors in the vehicle, compared with conventional wheeled mobile robots. An estimation of the wheel slip ratio is essential to improve the accuracy of locomotion control. In this paper, we propose an improved adaptive controller to allow WMR to track the desired trajectory under unknown longitudinal slip, where the stabilisation of the closed-loop tracking system is guaranteed by the Lyapunov theory. All system states use neural network online weight tuning algorithms, which ensure small tracking errors and no loss of stability in robot motion with bounded input signals. We demonstrate superior tracking results using the proposed control method in various Matlab simulations.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive motion control of wheeled mobile robot with unknown slippage

Gao

Song

Ding

et al. 2014

International Journal of Control

View full text Add to dashboard Cite

show abstract

“…), then the compensator control command will be , and, if u = u c + u o , we will haveAs shown in (14), the neural network is used as a straightforward compensator control law. The systems with dynamics that match Model II are very good cases for ANN compensation control 95–102, 105, 106. These systems are often mechanical systems whose behavior is explained through Newton's or Euler's laws.…”

Section: An Introduction To Neuro Controlmentioning

confidence: 99%

“…Recently, neural networks have been employed to tackle this problem, mainly by cancelling/compensating undesirable or uncertain parts of the system dynamics. In this category of control systems, the neural network is not the sole control law and there usually exist two 89, 95–99 or three 100–103 controllers working jointly. ANN control laws have already been used together with proportional 104, proportional‐integral‐derivative 99, 103, sliding mode (conventional 101 and intelligent 97, 98), back stepping 95, 100, 102, H ∞ ‐based robust 89, feedback linearization 89 and model reference adaptive 105 controllers.…”

Section: An Introduction To Neuro Controlmentioning

confidence: 99%

“…The control input is force or torque which appears alone (not multiplied by system parameters or states or as a function of them) in the corresponding model equations. In these problems, if linear or angular displacement is addressed, the control problem will be second order 89, 98, 100, 10, 102–104, and, if linear or angular velocity is controlled, the problem will be first order 95, 97, 105.…”

Section: An Introduction To Neuro Controlmentioning

confidence: 99%

See 1 more Smart Citation

A critical review of the most popular types of neuro control

Mohammadzaheri

Chen

Grainger

2011

Asian Journal of Control

View full text Add to dashboard Cite

In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well-known control technique. This attitude towards the extension of the application of well-known control methods using ANNs was followed by the development of ANN model-predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well-known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed.Key Words: Control, neural network, adaptive, feedback linearization, predictive, model reference, perceptron, radial basis. I. ARTIFICIAL NEURAL NETWORKS USABLE IN CONTROLArtificial neural networks (ANNs) are special mathematical models inspired by human neural networks. An ANN usually includes neurons, connections and biases. Neurons are arranged in 'layers'. There are a variety of neural networks suitable for different purposes [1,2]. In neuro control, it is a difficult and unsolved problem to find the best ANN structure for each specific application; thus, a fairly large ANN is usually employed to deal with relatively complex approximation problems [3]. In this paper, the most common types of artificial neural networks in the area of control are introduced: multi layer perceptrons (MLPs) and radial basis function networks (RBFNs). Both of these are known as universal approximators of systems [4,5]. The advantage of RBFNs is their quick training process compared with MLPs; however, for complicated systems with many inputs, the number of neurons in RBFNs are usually considerably higher than MLPs [1,2]. Regardless of the main structure, if the output of an ANN depends not only on the current q

show abstract

The Study of a Vision-Based Pedestrian Interception System

Fang

Zhang

2012

Intelligent Robotics and Applications

View full text Add to dashboard Cite

An artificial neural network based dynamic controller for a robot in a multi-agent system

Cited by 17 publications

References 23 publications

Adaptive motion control of wheeled mobile robot with unknown slippage

Adaptive motion control of wheeled mobile robot with unknown slippage

A critical review of the most popular types of neuro control

The Study of a Vision-Based Pedestrian Interception System

Contact Info

Product

Resources

About