M. Gopal

Bio: M. Gopal is an academic researcher from Indian Institutes of Technology. The author has contributed to research in topics: Control theory & Adaptive control. The author has an hindex of 3, co-authored 8 publications receiving 22 citations.

Self-organizing neural networks for learning inverse dynamics of robot manipulator

Abstract: Fast and accurate trajectory tracking of a robot arm primarily depends on the knowledge of its explicit inverse dynamics model. Online learning of inverse dynamics using a supervised learning algorithm is difficult in the absence of a priori knowledge of command error. On the other hand, a self-organizing neural network employing an unsupervised learning scheme does not depend on the command error. These networks are suitable for both off-line and online schemes of learning the inverse dynamics. The present paper proposes two schemes based on unsupervised learning algorithms, namely, Kohonen's self-organizing topology conserving feature map and "neural-gas" algorithm. Simulation results on a single link manipulator confirms the efficacy of the proposed schemes. >

Adaptive manipulator trajectory control using neural networks

Abstract: A unified study of adaptive control and neural network based control schemes for the trajectory tracking problem of robot manipulators is presented. Efficacy of parametrized adaptive algorithms in compensating the structured uncertainties in robot dynamics is verified through extensive simulation. The ability of neural networks to provide a robust adaptive framework in the presence of both structured and unstructured uncertainties is investigated. A case study is carried out in support of a parametrized adaptive scheme using neural networks. Simulation results clearly indicate that the neural network based adaptive controller achieves better tracking in the presence of parametric uncertainties as well as unmodelled effects compared to the simple direct adaptive scheme.

Robust trajectory control of a robot manipulator

Abstract: The tracking problem for a robotic manipulator with uncertain dynamics is considered. The proposed control scheme utilizes manipulator ‚inverse‘ as an adaptive feedforward controller, the controller gains are updated to cow with variations in the manipulator inverse due to changes the operating point A feedback conlroller that provides arbitrary assignment of all eigenvalues and certain parts o f 3 closed-loop eigenvector structure: is also used. Eigenstructure assignment is used to enhance closed-loop stability and to achieve robust tracking. Simulation results are presented in support of the proposed control scheme. The results demonstrate satisfactory performance of the controller despite variations in payload.

Eigenstructure assignment in robot tracking applications

Abstract: Design procedures based on exact eigenstructure assignment are not suitable because of very high computational requirements. A computation-effective control design procedure for eigenstructure assignment using aggregation is presented. Dominant eigenvalues are placed at specified locations in the complex plane and the non-dominant eigenvalues are placed in a specified disk. The proposed design procedure is applied to the trajectory tracking problem of a robot manipulator. An error-pattern based payload estimation and compensation scheme is also proposed to improve performance robustness.

Document Image Indexing Using Edit Distance Based Hashing

Abstract: We present a novel word image based document indexing scheme by combination of string matching and hashing The word image representation is defined by string codes obtained by unsupervised learning over graphical primitives The indexing framework is defined by distance based hashing function which does the object projection to hash space by preserving their distances We have used edit distance based string matching for defining the hashing function and for approximate nearest neighbor based retrieval The application of the proposed indexing framework is presented for two document image collections belonging to Devanagari and Bengali script

Bibliography of Self-Organizing Map (SOM) Papers: 1981-1997

Abstract: The Self-Organizing Map (SOM) algorithm has attracted an ever increasing amount of interest among researches and practitioners in a wide variety of elds The SOM and a variant of it, the LVQ, have been analyzed extensively, a number of variants of them have been developed and, perhaps most notably, they have been applied extensively within elds ranging from engineering sciences to medicine, biology, and economics We have collected a comprehensive list of 3343 scienti c papers that use the algorithms, have bene ted from them, or contain analyses of them The list is intended to serve as a source for literature surveys We have provided both a thematic and a keyword index to help nding articles of interest

Modification of Kohonen's SOFM to Simulate Cortical Plasticity Induced by Coactivation Input Patterns

Abstract: We present a modification of Kohonens SOFMin order to simulate cortical plasticity induced by coactivation patterns. This is accomplished by introducing a probabilistic mode of stimulus presentation and by substituting the winner-takes- all mechanism by selecting the winner from a set of best matching neurons.

Self-Organizing Feature Maps for Modeling and Control of Robotic Manipulators

Abstract: This paper presents a review of self-organizing feature maps (SOFMs), in particular, those based on the Kohonen algorithm, applied to adaptive modeling and control of robotic manipulators. Through a number of references we show how SOFMs can learn nonlinear input–output mappings needed to control robotic manipulators, thereby coping with important robotic issues such as the excess degrees of freedom, computation of inverse kinematics and dynamics, hand–eye coordination, path-planning, obstacle avoidance, and compliant motion. We conclude the paper arguing that SOFMs can be a much simpler, feasible alternative to MLP and RBF networks for function approximation and for the design of neurocontrollers. Comparison with other supervised/unsupervised approaches and directions for further work on the field are also provided.

Control system design for robots used in simulating dynamic force and moment interaction in virtual reality applications

Abstract: This dissertation presents an approach to simulating the dynamic force and moment interaction between a human and a virtual object using a robotic manipulator as the force transmitter. Accurate control of the linear and angular accelerations of the robot end effector is required in order for the correct forces and moments to be imparted on a human operating in a computer generated virtual environment. A control system has been designed which is robust in terms of stability and performance. This control system is derived from abbreviated linear and nonlinear models of the manipulator dynamics which are efficient enough for real-time implementation yet retain a sufficient level of complexity for accurate calculations. An efficient multiple-input multiple-output (MIMO) pole placement scheme has also been devised which locates the pre-specified system eigenvalues. The controller gains are given as explicit functions of a desired trajectory to be followed and, thus, are time varying such that the overall closed-loop system is rendered time-invariant. Key software elements were automatically derived and output in compiler-ready form demonstrating the feasibility of automatic, computer generated control laws for complex robotic systems. Test results are given for a PUMA 560 used to impart dynamic forces on a user operating in a virtual environment.