A neural network based surface roughness discrimination algorithm

This paper presents two approaches to surface roughness discrimination based on the use of a sensitive whisker system together with frequency spectrum analysis and neural networks classification methods. The key characteristic of the proposed methods is their ability to provide real-time feature classifications to help roboticspsila agents to scan their environmentpsilas properties such as objectpsilas location and textures, by performing motorized whiskers sweeps. Successful implementation of the system for flat orthogonal surfaces is demonstrated here. The results are validated based on both simulation and experiments using a hardware prototype.