|Abstract:||Visual-inertial odometry (VIO) is an accurate, inexpensive and complementary approach for land vehicle navigation in Global Navigation Satellite System (GNSS) signal-denied environments. VIO is subject to scale drift because it estimates forward direction translation using distant feature points that are generally located only in the forward direction. Wheel odometer measurement can be obtained from the CANBUS interface of most modern passenger vehicles and these provide reliable estimates of the forward wheel speed. In this paper, we present an innovative approach to incorporate wheel odometry and non-holonomic constraints (NHC) together with tightly-coupled monocular visual-inertial odometry using the Multi-State Constraint Kalman Filter (MSCKF) developed by Mourikis and Roumeliotis . The algorithm is first validated and tested on two publicly available datasets and then evaluated using real-world winter driving data collected in suburban and urban environments.|
Proceedings of the 33rd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2020)
September 21 - 25, 2020
|Pages:||2237 - 2251|
|Cite this article:||
Huang, Cheng, Jiang, Yang, O’Keefe, Kyle, "Wheel Odometry aided Visual-Inertial Odometry for Land Vehicle Navigation in Winter Urban Environments," Proceedings of the 33rd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2020), September 2020, pp. 2237-2251.
ION Members/Non-Members: 1 Download Credit