Raj Kumar

Work place: Electronics & Computer Engineering Department, IIT Roorkee, Roorkee, Hardwar

E-mail: rajkumar1chak@gmail.com


Research Interests: Computational Learning Theory, Control Theory, Logic Calculi


Raj kumar was born in Agra, India in 1987. He received bachelor of Engineering degree in Electronics and Communication Engineering from G.L.A. Institute of Tech & Management, Mathura. Currently he is pursuing M.Tech with specialization in System Modeling & Control in Electronics and Computer Department from Indian Institute of Technology Roorkee. His area of research includes Fuzzy logic Control, Reinforcement Learning.

Author Articles
Temporal Difference based Tuning of Fuzzy Logic Controller through Reinforcement Learning to Control an Inverted Pendulum

By Raj Kumar M. J. Nigam Sudeep Sharma Punitkumar Bhavsar

DOI: https://doi.org/10.5815/ijisa.2012.09.02, Pub. Date: 8 Aug. 2012

This paper presents a self-tuning method of fuzzy logic controllers. The consequence part of the fuzzy logic controller is self-tuned through the Q-learning algorithm of reinforcement learning. The off policy temporal difference algorithm is used for tuning which directly approximate the action value function which gives the maximum reward. In this way, the Q-learning algorithm is used for the continuous time environment. The approach considered is having the advantage of fuzzy logic controller in a way that it is robust under the environmental uncertainties and no expert knowledge is required to design the rule base of the fuzzy logic controller.

[...] Read more.
Supervised Online Adaptive Control of Inverted Pendulum System Using ADALINE Artificial Neural Network with Varying System Parameters and External Disturbance

By Sudeep Sharma Vijay Kumar Raj Kumar

DOI: https://doi.org/10.5815/ijisa.2012.08.07, Pub. Date: 8 Jul. 2012

Generalized Adaptive Linear Element (GADALINE) Artificial Neural Network (ANN) as an Artificial Intelligence (AI) technique is used in this paper to online adaptive control of a Non-linear Inverted Pendulum (IP) system. The ANN controller is designed with specifications as: network type is three (Input, Hidden and Output) layered Feed-Forward Network (FFN), training is done by Widrow-Hoffs delta rule or Least Mean Square algorithm (LMS), that updates weight and bias states to minimize the error function. The research is focused on how to adapt the control actions to solve the problem of “parameter variations”. The method is applied to the Nonlinear IP model with the application of some uncertainties, and the experimental results show that the system responds very well to handle those uncertainties.

[...] Read more.
Other Articles