The project aims to investigate intelligent systems that facilitate development of a low-cost assistive robotic device for people with severe movement disability. The objective is to devise a Brain-Computer Interface ( BCI ) that allows a highly disabled person to control a smart wheelchair and robotic manipulator combination by thought alone.
The project therefore investigates an EEG-based BCI operated asynchronously by the user, based on mapping of imagined-tasks related mental states to respective computer commands. Existing BCI systems are mainly driven synchronously under a computer control and lack sufficient accuracy and robustness primarily due to highly time-varying stochastic nature of EEG signal. Building on the promising results obtained from the UU’s recent work on advnaced BCI algorithms for feature extraction and pattern classification, this project involves investigating enhanced algorithms cabable of tracking time-varying probability-density-function associated with a stochastic EEG signal, so as to be able to devise a user driven asynchronous BCI. The intended user actions as interpreted by the BCI will be validated through a specially designed virtual keyboard, before forwarding to activate the wheelchair or the manipulator. Simultaneously a scene reader for reading visual map of the environment will be designed, using which the disabled person can point to the desired target.
For a full list of my publications please check this link.
To access my CV, please click this link.
Click this link to see the Video showing real-time robot control through Motor Imagery (MI).