SPIDAR calibration based on regression methods

M'Hamed Frad (1) , Hichem Maaref (1) , Samir Otmane (1) , Abdelatif Mtibaa (2)

1 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
2 EE Laboratory

In order to obtain accurate position estimation, it is imperative that the SPIDAR, a haptic interface device, is properly calibrated. The driving idea of this work is to derive easy-to-use calibration algorithms that can be used to calibrate our haptic device and to add therefore adaptability to the system behavior. We make use of regression methods and we obtain calibration algorithms as a solution to SPIDAR inaccuracy. The efficacy of the proposed methods is illustrated using experimental data collected from a sensor platform.

Mots clés: SPIDAR; Calibration; Characterization; Regression; Neural Network; Support Vector Machine

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Interface homme-machine [cs.HC]

M'Hamed Frad, Hichem Maaref, Samir Otmane, Abdelatif Mtibaa. SPIDAR calibration based on regression methods. 11th IEEE International Conference on Networking, Sensing and Control (ICNSC 2014), Apr 2014, Miami, FL, United States. pp.679--684, ⟨10.1109/ICNSC.2014.6819707⟩. ⟨hal-01016969⟩