AIVIO: Closed-loop, Object-relative Navigation of UAVs with AI-aided Visual Inertial Odometry

TL;DR

This paper introduces a real-time UAV navigation system that uses AI-based object pose estimation fused with inertial data, enabling effective object-relative navigation with minimal sensors for tasks like power pole inspection.

Contribution

The paper presents a novel UAV system combining synthetic-data-trained deep learning object pose estimation with IMU fusion for real-time, object-relative navigation using minimal sensors.

Findings

Successful real-world validation on power pole inspection tasks

Real-time performance with minimal sensor setup

Effective object-relative localization in challenging environments

Abstract

Object-relative mobile robot navigation is essential for a variety of tasks, e.g. autonomous critical infrastructure inspection, but requires the capability to extract semantic information about the objects of interest from raw sensory data. While deep learning-based (DL) methods excel at inferring semantic object information from images, such as class and relative 6 degree of freedom (6-DoF) pose, they are computationally demanding and thus often not suitable for payload constrained mobile robots. In this letter we present a real-time capable unmanned aerial vehicle (UAV) system for object-relative, closed-loop navigation with a minimal sensor configuration consisting of an inertial measurement unit (IMU) and RGB camera. Utilizing a DL-based object pose estimator, solely trained on synthetic data and optimized for companion board deployment, the object-relative pose measurements are fused with the IMU data to perform object-relative localization. We conduct multiple real-world experiments to validate the performance of our system for the challenging use case of power pole inspection. An example closed-loop flight is presented in the supplementary video.