english only
EPFL > STI > IMT > LASA > Publications > Abstract



We recorded 16 channels of EMG, motion capture and gaze data from a wearable gaze tracker, during targeted pick-and-place tasks. A single subject performed an experiment, in which a target was presented on a horizontal monitor, and an object was repositioned over the target. EMG data was evaluated using two SVRs and shown to have large errors in the x-direction, especially if only more proximal muscles were included. The gaze tracking was shown to be very fast and accurate in its directional estimation. We combined these modalities using a Kalman filter and preliminary results showed that gaze can improve prediction of the motion of the hand.


Downloadable files: 0) { $tempFile = $row['pdfFile']; $temp = "pdf"; echo "[$temp] "; } // ps.Z if (strlen($row['psZFile'])>0) { $tempFile = $row['psZFile']; $temp = "ps.Z"; echo "[$temp] "; } // ps.gz if (strlen($row['psgzFile'])>0) { $tempFile = $row['psgzFile']; $temp = "ps.gz"; echo "[$temp] "; } ?>



Last update: 25/08/06