Visual-Inertial-Wheel Odometry with Online Calibration

We introduce a novel visual-inertial-wheel odometry (VIWO) system for ground vehicles, which efficiently fuses multi-modal visual, inertial and 2D wheel odometry measurements in a sliding-window filtering fashion. As multi-sensor fusion requires both intrinsic and extrinsic (spatiotemproal) calibration parameters which may vary over time during terrain navigation, we propose to perform VIWO along with online sensor calibration of wheel encoders' intrinsic and extrinsic parameters. The video shows VIWO calibration performance during simulated general motion and planar motion scenarios, and comparison between calibrated and not calibrated system's localization in real-world, large-scale urban driving dataset.