PROBE: Predictive Robust Estimation for Visual-Inertial Navigation
This addresses navigation robustness in chaotic environments for robotics, but it is incremental as it builds on existing visual-inertial methods with a novel weighting technique.
The paper tackles the challenge of improving localization accuracy in visual-inertial navigation systems by learning a model to predict the quality of visual features and adjust their influence based on localization error, resulting in substantial error reductions on datasets including 4 km from KITTI and 700 m of indoor/outdoor driving.
Navigation in unknown, chaotic environments continues to present a significant challenge for the robotics community. Lighting changes, self-similar textures, motion blur, and moving objects are all considerable stumbling blocks for state-of-the-art vision-based navigation algorithms. In this paper we present a novel technique for improving localization accuracy within a visual-inertial navigation system (VINS). We make use of training data to learn a model for the quality of visual features with respect to localization error in a given environment. This model maps each visual observation from a predefined prediction space of visual-inertial predictors onto a scalar weight, which is then used to scale the observation covariance matrix. In this way, our model can adjust the influence of each observation according to its quality. We discuss our choice of predictors and report substantial reductions in localization error on 4 km of data from the KITTI dataset, as well as on experimental datasets consisting of 700 m of indoor and outdoor driving on a small ground rover equipped with a Skybotix VI-Sensor.