CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial Odometry

08/30/2022
by   Yingfu Xu, et al.
2

Learning-based visual ego-motion estimation is promising yet not ready for navigating agile mobile robots in the real world. In this article, we propose CUAHN-VIO, a robust and efficient monocular visual-inertial odometry (VIO) designed for micro aerial vehicles (MAVs) equipped with a downward-facing camera. The vision frontend is a content-and-uncertainty-aware homography network (CUAHN) that is robust to non-homography image content and failure cases of network prediction. It not only predicts the homography transformation but also estimates its uncertainty. The training is self-supervised, so that it does not require ground truth that is often difficult to obtain. The network has good generalization that enables "plug-and-play" deployment in new environments without fine-tuning. A lightweight extended Kalman filter (EKF) serves as the VIO backend and utilizes the mean prediction and variance estimation from the network for visual measurement updates. CUAHN-VIO is evaluated on a high-speed public dataset and shows rivaling accuracy to state-of-the-art (SOTA) VIO approaches. Thanks to the robustness to motion blur, low network inference time ( 23ms), and stable processing latency ( 26ms), CUAHN-VIO successfully runs onboard an Nvidia Jetson TX2 embedded processor to navigate a fast autonomous MAV.

READ FULL TEXT

page 1

page 4

page 7

page 9

page 13

page 14

page 16

page 17

research
03/14/2022

A Self-Supervised, Differentiable Kalman Filter for Uncertainty-Aware Visual-Inertial Odometry

Traditionally, visual-inertial-odometry (VIO) systems rely on filtering ...
research
11/30/2017

Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight

In recent years, vision-aided inertial odometry for state estimation has...
research
01/06/2021

CNN-based Visual Ego-Motion Estimation for Fast MAV Maneuvers

In the field of visual ego-motion estimation for Micro Air Vehicles (MAV...
research
10/19/2018

RaD-VIO: Rangefinder-aided Downward Visual-Inertial Odometry

State-of-the-art forward facing monocular visual-inertial odometry algor...
research
03/06/2018

Robust Odometry using Sensor Consensus Analysis

Odometry forms an important component of many manned and autonomous syst...
research
10/05/2021

Learned Uncertainty Calibration for Visual Inertial Localization

The widely-used Extended Kalman Filter (EKF) provides a straightforward ...
research
01/15/2020

Direct Visual-Inertial Ego-Motion Estimation via Iterated Extended Kalman Filter

This letter proposes a reactive navigation strategy for recovering the a...

Please sign up or login with your details

Forgot password? Click here to reset