Since Doug Engelbarts presentation in 1963, the general functionality of the computer mouse has hardly changed even though it shows several shortcomings, such as limited ergonomy, causing carpal tunnel syndrome. A pen, on the other hand, is much better suited as a pointing device and allows additional channels of control, e.g. by detecting rotation and inclination. With this thesis we will explore the possibilities of using a sensor-enhanced pen (DigiPen) as a computer pointing device, and key to its functionality is the elimination of drift by means of a reliable and robust standstill detection. Within this work there will be a strong cooperation with STABILO International GmbH and the development will also take place at the local level with STABILO (Heroldsberg). A prototype of the DigiPen, data sets, and developed software will be provided by STABILO.
The primary goal of this thesis is the development of a standstill detection of the DigiPen. The DigiPen is equipped with inertial sensors which allow the detection of movement. The sensors currently include a gyroscope, an accelerometer, a magnetometer and a force sensor, but an expansion by further sensors or actors is feasible. Several standstill detection approaches, like neural networks or sensor fusion should be implemented and evaluated.
- Basics of signal and data processing techniques
- Basics of Artificial Intelligence, in particular machine-learning methods
- Basic knowledge of MEMS-sensors
- Motivation and interest in solving technical problems independently