Mapping between different kinematic structures without absolute positioning during operation


- Dataset acquisition performed to the HANDLE project partner: Orebro University - AASS Learning Systems Lab.

- To study the motion of the human thumb finger relatively to the rest of the hand. To move the hand through all possible movements of the thumb several times.

- The acquired data was going to form a training set for an algorithm that learns the mapping from CyberGlove (human hand) values to SHADOW robotic hand joint angles, therefore it is important that the entire range of each joint is explored, and that there are as many samples as possible of as many different thumb positions as possible.


- 5 datasets of a human demonstrator performing different thumb movements. The hand of the human subject was equipped with a Cyberglove and several Polhemus Liberty magnetic tracker sensors. The demonstrations were also recorded using a monocular RGB camera. - Request access to HANDLE project database here. Sample dataset video:

- Publication by the HANDLE partner Orebro University - AASS Learning Systems Lab.: Berglund, E.; Iliev, B.; Palm, R.; Krug, R.; Charusta, K.; Dimitrov, D., "Mapping between different kinematic structures without absolute positioning during operation," Electronics Letters , vol.48, no.18, pp.1110,1112, August 30 2012. [ PDF]

- Teleoperation of robotic platforms performing dexterous manipulation tasks using the commands sent by a human operator using as interface the Cyberglove. Dissemination videos of HANDLE project (Euronews, European Commission, ...):

Scholarly Lite is a free theme, contributed to the Drupal Community by More than Themes.