# A Look at Improving Robustness in Visual-inertial SLAM by Moment Matching

arXiv: https://arxiv.org/abs/2205.13821 · HTML: https://mlsanity.com/paper/2205.13821/

## Key facts

- No citing papers in the map yet (data through 13 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 27 May 2022.

## Builds on (most cited first, 9 of 9)

- [Expectation Propagation for approximate Bayesian inference](https://mlsanity.com/paper/1301.2294/) (2013)
- [Visual-Inertial Mapping with Non-Linear Factor Recovery](https://mlsanity.com/paper/1904.06504/) (2019)
- [Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight](https://mlsanity.com/paper/1712.00036/) (2017)
- [Fast Variational Learning in State-Space Gaussian Process Models](https://mlsanity.com/paper/2007.04731/) (2020)
- [Bayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees](https://mlsanity.com/paper/2111.01721/) (2021)
- [State Space Expectation Propagation: Efficient Inference Schemes for Temporal Gaussian Processes](https://mlsanity.com/paper/2007.05994/) (2020)
- [HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry](https://mlsanity.com/paper/2106.11857/) (2021)
- [An EKF-SLAM algorithm with consistency properties](https://mlsanity.com/paper/1510.06263/) (2015)
- [PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation](https://mlsanity.com/paper/1708.00894/) (2017)

## Abstract (arXiv)

The fusion of camera sensor and inertial data is a leading method for ego-motion tracking in autonomous and smart devices. State estimation techniques that rely on non-linear filtering are a strong paradigm for solving the associated information fusion task. The de facto inference method in this space is the celebrated extended Kalman filter (EKF), which relies on first-order linearizations of both the dynamical and measurement model. This paper takes a critical look at the practical implications and limitations posed by the EKF, especially under faulty visual feature associations and the presence of strong confounding noise. As an alternative, we revisit the assumed density formulation of Bayesian filtering and employ a moment matching (unscented Kalman filtering) approach to both visual-inertial odometry and visual SLAM. Our results highlight important aspects in robustness both in dynamics propagation and visual measurement updates, and we show state-of-the-art results on EuRoC MAV drone data benchmark.