Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Neural networks for control systems: a survey
Automatica (Journal of IFAC)
Introduction to Robotics: Mechanics and Control
Introduction to Robotics: Mechanics and Control
Transparency improvement in haptic devices with a torque compensator using motor current
EuroHaptics'12 Proceedings of the 2012 international conference on Haptics: perception, devices, mobility, and communication - Volume Part I
Hi-index | 0.00 |
In robot manipulators, optical incremental encoders are widely used asthe transducers to monitor joint position and velocity information. Withincremental encoder, positional information is determined as discrete datarelative to a reference (home) position. However, velocity information canonly be deduced by processing the position data. In this paper, a method ofusing a neural network to estimate the velocity information of robotic jointfrom discrete position versus time data is proposed and evaluated. Thearchitecture of the neural net and the training methodology are presentedand discussed.This approach is then applied to estimate the joint velocity of a SCARArobot while performing an electronic component assembly task. Based oncomputer simulations, comparison of the accuracy of the neural networkestimator with two other well established velocity estimation algorithms aremade. The neural net approach can maintain good performance even in thepresence of measurement noises.