# MPVO: Motion-Prior based Visual Odometry for PointGoal Navigation

arXiv: https://arxiv.org/abs/2411.04796 · HTML: https://mlsanity.com/paper/2411.04796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects](https://mlsanity.com/paper/2006.13171/) (2020)
- [Cognitive Mapping and Planning for Visual Navigation](https://mlsanity.com/paper/1702.03920/) (2017)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Rearrangement: A Challenge for Embodied AI](https://mlsanity.com/paper/2011.01975/) (2020)
- [TartanVO: A Generalizable Learning-based VO](https://mlsanity.com/paper/2011.00359/) (2020)
- [UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering](https://mlsanity.com/paper/2102.11870/) (2021)
- [Is Mapping Necessary for Realistic PointGoal Navigation?](https://mlsanity.com/paper/2206.00997/) (2022)
- [Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation](https://mlsanity.com/paper/2105.07593/) (2021)
- [Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents](https://mlsanity.com/paper/2009.03231/) (2020)
- [The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation](https://mlsanity.com/paper/2108.11550/) (2021)
- [DoRO: Disambiguation of referred object for embodied agents](https://mlsanity.com/paper/2207.14205/) (2022)
- [Teledrive: An Embodied AI based Telepresence System](https://mlsanity.com/paper/2406.00375/) (2024)

## Abstract (arXiv)

Visual odometry (VO) is essential for enabling accurate point-goal navigation of embodied agents in indoor environments where GPS and compass sensors are unreliable and inaccurate. However, traditional VO methods face challenges in wide-baseline scenarios, where fast robot motions and low frames per second (FPS) during inference hinder their performance, leading to drift and catastrophic failures in point-goal navigation. Recent deep-learned VO methods show robust performance but suffer from sample inefficiency during training; hence, they require huge datasets and compute resources. So, we propose a robust and sample-efficient VO pipeline based on motion priors available while an agent is navigating an environment. It consists of a training-free action-prior based geometric VO module that estimates a coarse relative pose which is further consumed as a motion prior by a deep-learned VO model, which finally produces a fine relative pose to be used by the navigation policy. This strategy helps our pipeline achieve up to 2x sample efficiency during training and demonstrates superior accuracy and robustness in point-goal navigation tasks compared to state-of-the-art VO method(s). Realistic indoor environments of the Gibson dataset is used in the AI-Habitat simulator to evaluate the proposed approach using navigation metrics (like success/SPL) and pose metrics (like RPE/ATE). We hope this method further opens a direction of work where motion priors from various sources can be utilized to improve VO estimates and achieve better results in embodied navigation tasks.