SS15 - Directional Estimation

Many estimation problems of practical relevance include the  problem of  estimating directional quantities, for example angular values  or  orientations. However, conventional filters like the Kalman-Filter   assume Gaussian distributions defined on R^n. This assumption neglects   the inherent periodicity present in directional quantities. Consequently, more sophisticated approaches are required to accurately   describe the circular setting. 

This  Special Session addresses fundamental techniques, recent  developments  and future research directions in the field of estimation  involving  directional and periodic data. 

Topics of interest

•  estimation of circular or directional quantities 
•  6 DOF pose estimation 
•  Circular and directional statistics 
•  Statistics on the rotation group $SO(3)$ and other manifolds 
•  IMU based estimation of rotation 
•  recursive and batch filtering in a periodic setting 
•  Applications: tracking, robotics, medicine, biology 

Keywords

directional statistics, periodicity, pose estimation, orientation, rotations, estimation on manifolds 

Special Session Organizers

• Uwe D. Hanebeck, Karlsruhe  Institute of Technology (Germany)
• Gerhard Kurz, Karlsruhe  Institute of Technology (Germany)
• Igor Gilitschenski, Karlsruhe  Institute of Technology (Germany)

Special Session Contact

• Uwe D. Hanebeck ()
• Gerhard Kurz ()
• Igor Gilitschenski ()