# xVIO: A Range-Visual-Inertial Odometry Framework

arXiv: https://arxiv.org/abs/2010.06677 · HTML: https://mlsanity.com/paper/2010.06677/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Exploring Event Camera-based Odometry for Planetary Robots](https://mlsanity.com/paper/2204.05880/) (2022)
- [Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry](https://mlsanity.com/paper/2209.06588/) (2022)
- [Optimizing Terrain Mapping and Landing Site Detection for Autonomous UAVs](https://mlsanity.com/paper/2205.03522/) (2022)
- [Online Adaptation of Visual Odometry Frontends with Image-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2603.21785/) (2026)
- [Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension](https://mlsanity.com/paper/2606.06790/) (2026)

## Abstract (arXiv)

xVIO is a range-visual-inertial odometry algorithm implemented at JPL. It has been demonstrated with closed-loop controls on-board unmanned rotorcraft equipped with off-the-shelf embedded computers and sensors. It can operate at daytime with visible-spectrum cameras, or at night time using thermal infrared cameras. This report is a complete technical description of xVIO. It includes an overview of the system architecture, the implementation of the navigation filter, along with the derivations of the Jacobian matrices which are not already published in the literature.