PROBE: Predictive robust estimation for visual-inertial navigation
Authors:
- 1 September 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3668-3675
Abstract
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.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- An iterative Kalman smoother for robust 3D localization on mobile and wearable devices2015
- Keyframe-based visual–inertial odometry using nonlinear optimizationThe International Journal of Robotics Research, 2014
- CELLO-EM: Adaptive sensor models without ground truth2013
- Information fusion in navigation systems via factor graph based incremental smoothingRobotics and Autonomous Systems, 2013
- StereoScan: Dense 3d reconstruction in real-time2011
- Robust Real-Time Visual Odometry with a Single Camera and an IMU2011
- Combined Visual and Inertial Navigation for an Unmanned Aerial Vehicle2008
- Learning an Outlier-Robust Kalman Filter2007
- A Multi-State Constraint Kalman Filter for Vision-aided Inertial NavigationProceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164), 2007
- Visual odometry on the Mars exploration rovers - a tool to ensure accurate driving and science imagingIEEE Robotics & Automation Magazine, 2006