# Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents

arXiv: https://arxiv.org/abs/2009.03231 · HTML: https://mlsanity.com/paper/2009.03231/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2020.

## Built on by (most cited first, 27 of 27)

- [ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation](https://mlsanity.com/paper/2301.13166/) (2023)
- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [Coupling Vision and Proprioception for Navigation of Legged Robots](https://mlsanity.com/paper/2112.02094/) (2021)
- [Curious Representation Learning for Embodied Intelligence](https://mlsanity.com/paper/2105.01060/) (2021)
- [Is Mapping Necessary for Realistic PointGoal Navigation?](https://mlsanity.com/paper/2206.00997/) (2022)
- [Episodic Memory Question Answering](https://mlsanity.com/paper/2205.01652/) (2022)
- [The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation](https://mlsanity.com/paper/2108.11550/) (2021)
- [Last-Mile Embodied Visual Navigation](https://mlsanity.com/paper/2211.11746/) (2022)
- [Learned Visual Navigation for Under-Canopy Agricultural Robots](https://mlsanity.com/paper/2107.02792/) (2021)
- [Embodied AI-Driven Operation of Smart Cities: A Concise Review](https://mlsanity.com/paper/2108.09823/) (2021)
- [Object Manipulation via Visual Target Localization](https://mlsanity.com/paper/2203.08141/) (2022)
- [Modality-invariant Visual Odometry for Embodied Vision](https://mlsanity.com/paper/2305.00348/) (2023)
- [ObjectReact: Learning Object-Relative Control for Visual Navigation](https://mlsanity.com/paper/2509.09594/) (2025)
- [SegMASt3R: Geometry Grounded Segment Matching](https://mlsanity.com/paper/2510.05051/) (2025)
- [Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics](https://mlsanity.com/paper/2304.12289/) (2023)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [ROS-X-Habitat: Bridging the ROS Ecosystem with Embodied AI](https://mlsanity.com/paper/2109.07703/) (2021)
- [Robust Navigation with Cross-Modal Fusion and Knowledge Transfer](https://mlsanity.com/paper/2309.13266/) (2023)
- [Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment](https://mlsanity.com/paper/2210.00413/) (2022)
- [Active Semantic Localization with Graph Neural Embedding](https://mlsanity.com/paper/2305.06141/) (2023)
- [MASt3R-Nav: WayPixel Navigation in Relative 3D Maps](https://mlsanity.com/paper/2605.24111/) (2026)
- [Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck](https://mlsanity.com/paper/2109.08677/) (2021)
- [Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks](https://mlsanity.com/paper/2402.12067/) (2024)
- [Solving Vision Tasks with Simple Photoreceptors Instead of Cameras](https://mlsanity.com/paper/2406.11769/) (2024)
- [Simultaneous Localization and Affordance Prediction of Tasks from Egocentric Video](https://mlsanity.com/paper/2407.13856/) (2024)
- [MPVO: Motion-Prior based Visual Odometry for PointGoal Navigation](https://mlsanity.com/paper/2411.04796/) (2024)
- [PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops](https://mlsanity.com/paper/2607.12811/) (2026)

## Abstract (arXiv)

Recent work has presented embodied agents that can navigate to point-goal targets in novel indoor environments with near-perfect accuracy. However, these agents are equipped with idealized sensors for localization and take deterministic actions. This setting is practically sterile by comparison to the dirty reality of noisy sensors and actuations in the real world -- wheels can slip, motion sensors have error, actuations can rebound. In this work, we take a step towards this noisy reality, developing point-goal navigation agents that rely on visual estimates of egomotion under noisy action dynamics. We find these agents outperform naive adaptions of current point-goal agents to this setting as well as those incorporating classic localization baselines. Further, our model conceptually divides learning agent dynamics or odometry (where am I?) from task-specific navigation policy (where do I want to go?). This enables a seamless adaption to changing dynamics (a different robot or floor type) by simply re-calibrating the visual odometry model -- circumventing the expense of re-training of the navigation policy. Our agent was the runner-up in the PointNav track of CVPR 2020 Habitat Challenge.