O(N) Recursive Algorithm for the Operational Space Inertia Matrix of a Robot Manipulator

The paper introduces artificial neural networks for the conventional control of robotic systems for better tracking performance. Different advanced dynamic control techniques are explained and a new second order recursive algorithm has been developed to tune the weights of the neural network. The problem of real-time control of a Pendubot system in difficult situations has been addressed. Examples, such as positioning and balancing structures, are presented and performances are compared to a conventional PD controller.

Download Full-text

Design and its characteristic analysis of a wheeled train uncoupling robot with multi-degrees-of-freedom

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science ◽

10.1177/0954406215582017 ◽

2015 ◽

Vol 230 (10) ◽

pp. 1673-1684 ◽

Cited By ~ 2

Author(s):

Jianjun Yao ◽

Yuxuan Huang ◽

Guilin Jiang ◽

Shuang Gao ◽

Rui Xiao ◽

...

Keyword(s):

Degrees Of Freedom ◽

Robot Manipulator ◽

Vital Role ◽

Real Time Control ◽

Characteristic Analysis ◽

Time Control ◽

Operational Space ◽

Wheeled Robot ◽

Marshalling Yard ◽

Cargo Transportation

Freight trains play a vital role in cargo transportation in the world. The freight cars need to be redistributed for marshalling according to different destinations in the hump yard. Humans are usually employed to uncouple the freight cars in the marshalling yard. However, the work environment is difficult to work in, because of its potential danger and the effects of the surrounding environment can have a very serious impact on human’s health. A wheeled robot is developed to replace humans to finish the uncoupling task. It has four degrees-of-freedom with flexible motion. Based on the D-H method, the kinematics, including the forward and the inverse kinematics, is firstly analysed. The dynamic analysis is then studied by Newton–Euler equations. The workspace is lastly investigated to verify its operational space such that the coupler can be easily reached by the robot manipulator. Those characteristic analyses provide a basis for motion planning and real-time control of the robot.

Download Full-text

Forward Models for Following a Moving Target with the Puma 560 Robot Manipulator

INTELIGENCIA ARTIFICIAL ◽

10.4114/intartif.vol18iss56pp31-42 ◽

2015 ◽

Vol 18 (56) ◽

pp. 31

Author(s):

Daniel Fernando Tello Gamarra ◽

Marco Antonio De Souza Leite Cuadros

Keyword(s):

Neural Networks ◽

Robot Manipulator ◽

Forward Model ◽

Control Architecture ◽

Moving Target ◽

Rbf Neural Networks ◽

Forward Models ◽

Operational Space ◽

Manipulator Robot

This paper describes how a forward model could be applied in a manipulator robot to accomplish the task of following a moving target. The forward model has been implemented in the puma 560 robot manipulator in simulation after a babbling motor phase using ANFIS neural networks. The forward model delivers a rough estimation of the position in the operational space of a moving target. Using this information a Cartesian controller tracks the moving target. An implementation of the proposed architecture and the Piepmeir algorithm for the problem of following a moving target is also shown in the paper. The control architecture proposed in this paper was also tested with MLP and RBF neural networks. Results and simulations are shown to demonstrate the applicability of our proposed architecture for tracking a moving target.

Download Full-text

A proof of the Ge–Lee statement on the inertia regressor of robot manipulators

Robotica ◽

10.1017/s0263574712000033 ◽

2012 ◽

Vol 31 (1) ◽

pp. 55-59 ◽

Cited By ~ 1

Author(s):

Juan Ignacio Mulero-Martínez

Keyword(s):

Degrees Of Freedom ◽

Robot Manipulator ◽

Robot Manipulators ◽

Formal Proof ◽

Nonlinear Functions ◽

Inertia Matrix

SUMMARYThis paper delivers a proof of a statement due to Ge and Lee. Specifically, these authors stated, without proof, that the entries of the inertia matrix may be completely parameterized by stacking elements of a regressor superset. This superset has the advantage of avoiding to derive the complete dynamics of a robot manipulator. On the basis of both mechanics and combinatorial arguments, we deliver a formal proof. In addition, we improve the estimations by sorting joint variables and partitioning the inertia matrix that results into the reduction of the regressor superset. The number of nonlinear functions in the regressor is also quantified. A 2 degrees of freedom revolute robot is presented to illustrate these ideas.

Download Full-text

Efficient O(N) recursive computation of the operational space inertia matrix

IEEE Transactions on Systems Man and Cybernetics ◽

10.1109/21.260669 ◽

1993 ◽

Vol 23 (5) ◽

pp. 1384-1391 ◽

Cited By ~ 16

Author(s):

K.W. Lilly ◽

D.E. Orin

Keyword(s):

Operational Space ◽

Inertia Matrix ◽

Recursive Computation

Download Full-text

Recursive Composite Adaptation for Robot Manipulators

Journal of Dynamic Systems Measurement and Control ◽

10.1115/1.4007557 ◽

2012 ◽

Vol 135 (2) ◽

Cited By ~ 2

Author(s):

Hanlei Wang

Keyword(s):

Adaptive Control ◽

Computational Complexity ◽

Prediction Error ◽

Robot Manipulators ◽

Recursive Algorithm ◽

Degree Of Freedom ◽

Inertia Matrix ◽

Adaptation Law ◽

Six Degree Of Freedom ◽

Composite Adaptive Control

In this paper, we investigate the recursive implementation of composite adaptive control for robot manipulators. Via exploitation of the relation between the inertia matrix and the Coriolis and centrifugal matrix, we present the recursive algorithm for the derivation of the filtered manipulator model, which, to our knowledge, is the first result on this point in the literature. With this filtered model, the prediction error of the filtered torque is obtained and injected to the direct adaptation, forming the well-known composite adaptation law, with an acceptable amount of computation O(n2). A six degree-of-freedom (DOF) manipulator is employed as a simulation example to show the performance and the computational complexity of the proposed recursive algorithm.

Download Full-text