Technical Paper presented at Robotics and Automation Conference

The research team at project partner FORTH from Greece has presented a technical paper related to their work in the SOPRANO project titled "Efficient Pose Prediction with Rational Regression Applied to vSLAM" at the IEEE International Conference on Robotics and Automation (ICRA) held in in Yokohama, Japan on 13-17 May.

Abstract:

Compared to polynomial splines, rational functions are known to be more efficient and well-behaved data fitting models. However, due to the potential presence of zeros in their denominator, rational functions tend to yield notoriously hard optimization problems. In this work, we present a novel least squares method for 6D pose prediction that employs rational regression. Our method can accommodate fixed data points and is able to circumvent the occurrence of zeros for rational quadratic interpolants. We demonstrate the suitability of rational quadratics for pose prediction by applying our approach to real data from the feature tracking stage of a real-time visual SLAM system and showing that it yields far more stable predictions when compared to state-of-the-art rational and polynomial spline methods.

Download: Link