Identifying contact formations from force signals: a comparison of fuzzy and neural network classifiers
- 22 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1623-1628
- https://doi.org/10.1109/icnn.1997.614137
Abstract
In this paper, we present and compare two methodsof identifying single-ended contact formations fromforce sensor patterns. Instead of using geometric modelsof the workpieces, both methods use force sensorsignals only. In the first method, fuzzy logic is usedto model the patterns in the force signals. Membershipfunctions are generated automatically from trainingdata and then used by the fuzzy classifier. In thesecond method, a neural network architecture is usedto learn the mapping from ...Keywords
This publication has 5 references indexed in Scilit:
- Identification and verification of termination conditions in fine motion in presence of sensor errors and geometric uncertaintiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Identifying contact formations from sensory patterns and its applicability to robot programming by demonstrationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Frequency-domain force measurements for discrete event contact recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Force sensing from human demonstration using a hybrid dynamical model and qualitative reasoningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Teaching and learning of compliance using neural nets: representation and generation of nonlinear compliancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002