A comparison of EKF and SGD applied to a view-based SLAM approach with omnidirectional images

• Proposal to overcome the influence of the non-linear errors on traditional visual SLAM methods.
• We focus on a highly non-linear observation model: the omnidirectional.
• Comparison of traditional filters like EKF, versus SGD.
• Compact map representation, consisting of a reduced set of omnidirectional views.
• We compare accuracy, robustness against errors and speed of convergence.

The problem of Simultaneous Localization and Mapping (SLAM) is essential in mobile robotics. The obtention of a feasible map of the environment poses a complex challenge, since the presence of noise arises as a major problem which may gravely affect the estimated solution. Consequently, a SLAM algorithm has to cope with this issue but also with the data association problem. The Extended Kalman Filter (EKF) is one of the most traditionally implemented algorithms in visual SLAM. It linearizes the movement and the observation model to provide an effective online estimation. This solution is highly sensitive to non-linear observation models as it is the omnidirectional visual model. The Stochastic Gradient Descent (SGD) emerges in this work as an offline alternative to minimize the non-linear effects which deteriorate and compromise the convergence of traditional estimators. This paper compares both methods applied to the same approach: a navigation robot supported by an efficient map model, established by a reduced set of omnidirectional image views. We present a series of real data experiments to assess the behavior and effectiveness of both methods in terms of accuracy, robustness against errors and speed of convergence.