Radar-Inertial Odometry For Computationally Constrained Aerial Navigation
Jan Michalczyk
TL;DR
This work addresses UAV localization in GNSS-denied and visually challenging environments by fusing a lightweight FMCW radar with an IMU. It develops multiple Radar-Inertial Odometry (RIO) approaches, including tightly-coupled Extended Kalman Filters with distance, Doppler, and measurement trails, a multi-state EKF with persistent landmarks, and a sliding-window factor-graph Rio, all capable of real-time operation on embedded hardware. A key contribution is the integration of online extrinsic calibration and, in parallel, a learning-based framework to predict robust radar 3D point correspondences, enabling improved data association in sparse, noisy radar scans. The methods demonstrate strong performance in indoor and foggy conditions, including closed-loop flights, and show competitive accuracy with vision-based systems while maintaining resilience to environmental degradation. The work also provides open-source implementations and datasets, highlighting practical viability for small-UAV autonomy under compute and sensing constraints.
Abstract
Recently, the progress in the radar sensing technology consisting in the miniaturization of the packages and increase in measuring precision has drawn the interest of the robotics research community. Indeed, a crucial task enabling autonomy in robotics is to precisely determine the pose of the robot in space. To fulfill this task sensor fusion algorithms are often used, in which data from one or several exteroceptive sensors like, for example, LiDAR, camera, laser ranging sensor or GNSS are fused together with the Inertial Measurement Unit (IMU) measurements to obtain an estimate of the navigation states of the robot. Nonetheless, owing to their particular sensing principles, some exteroceptive sensors are often incapacitated in extreme environmental conditions, like extreme illumination or presence of fine particles in the environment like smoke or fog. Radars are largely immune to aforementioned factors thanks to the characteristics of electromagnetic waves they use. In this thesis, we present Radar-Inertial Odometry (RIO) algorithms to fuse the information from IMU and radar in order to estimate the navigation states of a (Uncrewed Aerial Vehicle) UAV capable of running on a portable resource-constrained embedded computer in real-time and making use of inexpensive, consumer-grade sensors. We present novel RIO approaches relying on the multi-state tightly-coupled Extended Kalman Filter (EKF) and Factor Graphs (FG) fusing instantaneous velocities of and distances to 3D points delivered by a lightweight, low-cost, off-the-shelf Frequency Modulated Continuous Wave (FMCW) radar with IMU readings. We also show a novel way to exploit advances in deep learning to retrieve 3D point correspondences in sparse and noisy radar point clouds.