Search Results - "de Angulo, V.R."

Learning Inverse Kinematics: Reduced Sampling Through Decomposition Into Virtual Robots by de Angulo, V.R., Torras, C.

“…We propose a technique to speedup the learning of the inverse kinematics of a robot manipulator by decomposing it into two or more virtual robot arms. Unlike…”
Get full text

Speeding up the learning of robot kinematics through function decomposition by de Angulo, V.R., Torras, C.

“…The main drawback of using neural networks or other example-based learning procedures to approximate the inverse kinematics (IK) of robot arms is the high…”
Get full text

Rapid learning of humanoid body schemas with Kinematic Bézier Maps by Ulbrich, S., de Angulo, V.R., Asfour, T., Torras, C., Dillmann, R.

“…This paper addresses the problem of hand-eye coordination and, more specifically, tool-eye recalibration of humanoid robots. Inspired by results from…”
Get full text

Self-calibration of a space robot by de Angulo, V.R., Torras, C.

“…We present a neural-network method to recalibrate automatically a commercial robot after undergoing wear or damage, which works on top of the nominal inverse…”
Get full text

On-line learning with minimal degradation in feedforward networks by de Angulo, V.R., Torras, C.

“…Dealing with nonstationary processes requires quick adaptation while at the same time avoiding catastrophic forgetting. A neural learning technique that…”
Get full text