SPIDAR Calibration based on neural networks versus optical tracking
Résumé
This paper aims to present all the study done on the SPIDAR tracking and haptic device, in order to improve accuracy on the given position. Firstly we proposed a new semi-automatic initialization technique for this device using an optical tracking system. We also propose an innovative way to perfom calibration of 3D tracking device using virtual reality. Then, we used a two-layered feedforward neural network to reduce the location errors. We obtained very good results with this calibration, since we reduced the mean error by more than 50%.