Neural network method for haptic device calibration using an optic-haptic hybrid tracker

Abstract : The purpose of this paper is to asses to what extent an optical tracking system used for position tracking in virtual reality can be enhanced by combining it with a human scale haptic device named SPIDAR. The major advantage of this haptic device is the fact it is not dependent of free line-of-sight and unobtrusive. Unfortunately, the accuracy of the is affected by bad-tailored design. We explore to what extent the influence of these inaccuracies can be compensated by collecting precise information on the nonlinear error by using the optical tracking system and applying neural network regression (NN) for calibrating the haptic device reports. After calibration of the SPIDAR, we have found that the average error in position readings has reduced significantly. These results encourage the development of a hybrid optic-haptic system for virtual reality applications where the haptic device acts as an auxiliary source of position information for the optical tracking system.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01504243
Contributor : Frédéric Davesne <>
Submitted on : Sunday, April 9, 2017 - 11:51:20 AM
Last modification on : Monday, October 28, 2019 - 10:50:22 AM

Identifiers

  • HAL Id : hal-01504243, version 1

Citation

M'Hamed Frad, Hichem Maaref, Samir Otmane, Abdelatif Mtibaa. Neural network method for haptic device calibration using an optic-haptic hybrid tracker. International journal of applied engineering research (IJAER), 2016, 11 (11), pp.7420--7425. ⟨hal-01504243⟩

Share

Metrics

Record views

147