Visual Inertial Odometry Sensor Fusion Approach for Autonomous Localization

Citation Author(s):
Simone
Godio
Politecnico di Torino
Submitted by:
Simone Godio
Last updated:
Fri, 04/30/2021 - 12:20
DOI:
10.21227/10av-kj18
License:
19 Views
Categories:
0
0 ratings - Please login to submit your rating.

Abstract 

This paper describes a sensor fusion technique to localize autonomously unmanned vehicles. In particular, we performed a sensor fusion based on the extended Kalman filter between two commercial sensors. The adopted sensors are ZED2 and Intel T265, respectively; these platforms already perform visual-inertial odometry in their integrated system-on-chip. Since these 2 devices represent the top of the range on the market to make an autonomous localization, this study aims to analyze and inform about results that can be obtained by performing a sensor fusion between the two cameras. Several tests on a specific trajectory and environment demonstrated that a more robust autonomous localization than one of the single cameras can be obtained by properly tuning parameters and inputs of the Extended Kalman filter.

Instructions: 

rl                    -> 'EKF results txt file'

t265              -> 'Intel t265 results txt file'

ZED2            -> 'ZED2 results txt file'

paper.fig     -> 3D result graph shown in the paper (Fig. 10)

fig1.fig         -> Z-error shown in the paper (Fig. 11)

fig2.fig         -> XY results shown in the paper (Fig. 12)

test_1.m      -> Matlab file to manage data