Safe Mobility Using Autonomous Wheelchair Controlled By Human Cognition Using Riemannian Geometry

This dissertation proposes a novel framework that integrates an autonomous wheelchair with a brain computing interface which is implemented using the concepts of Riemannian Geometry. The cognitive-control model exploits the geometrical structure of Riemannian manifolds and piece-wise geodesics under a Bayesian framework, while accurately and quickly classifying the brain signals to command the wheelchair. The brain computer interface is implemented on an embedded GPU enabled computational system. The following is proposed:1. An EEG Signal classification model that uses concepts of Riemannian Geometry to output a command to control an intelligent Wheelchair. 2. Control architecture to control an autonomous wheelchair using the commands generated by the human brain. 3. Implementing the technology on an autonomous vehicle that can be controlled by human cognition using EEG Riemannian manifolds are nonlinear and this property enables effective description of dynamic processes of activities involving non-planar movement, which lie on a nonlinear manifold other than a vector space. Low dimensional data points on the manifolds provide highly efficient in providing the video features, which maintaining the crucial properties like geometry and topology. The Riemannian geometry provides a way to measure the distances/dissimilarities between different objects on the nonlinear manifold, hence it is a suitable tool for classification and tracking. The proposed model is also compared with two most relevant manifold tracking methods. Results have shown much improved tracking performance in terms of tracking drift and tightness and accuracy of tracked objects.