Inertial-Based Gesture Recognition for Artificial Intelligent Cockpit Control using Hidden Markov Models

Driving a car is no longer just a means to get around quickly. Currently, driving itself has become an entertainment factor with steadily increasing occupant safety. This is ensured by a multitude of safety and comfort features, such as various driver assistance systems and innovative control options within the cockpit. The content of this paper introduces a new way to cockpit operation, which contributes to the increase of user comfort. For gesture recognition of the occupant low-cost inertial sensors on a bracelet are used. Due to the relatively poor sensor performance, complex analysis algorithms are needed. For this purpose, the implementation of Hidden Markov models for the establishment of an artificially intelligent data analysis system is suitable. The present work is based on past research results performed at the CCASS, which provided a framework for reference-less human motion analysis and validation using low-cost inertial motion sensors. The developed algorithms are based on the theory of Hidden Markov Models for the stochastic modelling of human motion using Markov chains. In the present work the algorithm will be adapted to a concept of gesture recognition for cockpit control.