Community Research and Development Information Service - CORDIS

Abstract

This paper presents a new technique for the calibration of robots based on a neural network approach for the identification of non-geometrical errors. Although the identification of geometrical errors is no longer a problem, non-geometrical errors modelling is a very complex process. This paper uses a neural network approach avoiding explicit modelling of this kind of error. Simulations have been carried out on a robot with 6 degrees of freedom. Two compensation algorithms are presented, based on the improved knowledge of the model: the first one is based on the construction of a false target, the second one compensates directly into the joint space.

Additional information

Authors: RENDERS J-M, Université Libre de Bruxelles, Laboratoire d'Automatique, Bruxelles (BE);MILLAN J DEL R, JRC Ispra (IT);BECQUET M, JRC Ispra (IT)
Bibliographic Reference: Paper presented: The European Robotics and Intelligent Systems Conference, Corfu (GR), June 23-28, 1991
Availability: Available from (1) as Paper EN 36277 ORA
Record Number: 199111347 / Last updated on: 1994-12-02
Category: PUBLICATION
Original language: en
Available languages: en
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top