Gaussian process estimation of odometry errors for localization and mapping

Since early in robotics the performance of odometrytechniques has been of constant research for mobile robots. This is due to its direct influence on localization. The pose error grows unbounded in dead-reckoningsystems and its uncertainty has negative impacts in localization and mapping (i.e. SLAM). The dead-reckoningperformance in terms of residuals, i.e. the difference between the expected and the real pose state, is related to the statistical error or uncertainty in probabilistic motion models. A novel approach to model odometryerrors using Gaussian processes (GPs) is presented. The methodology trains a GP on the residual between the non-linear parametric motion model and the ground truth training data. The result is a GP over odometryresiduals which provides an expected value and its uncertainty in order to enhance the belief with respect to the parametric model. The localization and mapping benefits from a comprehensive GP- odometryresiduals model. The approach is applied to a planetary rover in an unstructured environment. We show that our approach enhances visual SLAMby efficiently computing image frames and effectively distributing keyframes.