# RingNav: Task-Shaped Circular Memory for Visual Heading

arXiv: https://arxiv.org/abs/2610.19044 · HTML: https://mlsanity.com/paper/2610.19044/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 16 of 16)

- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [A micro Lie theory for state estimation in robotics](https://mlsanity.com/paper/1812.01537/) (2018)
- [A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones](https://mlsanity.com/paper/1805.01831/) (2018)
- [GapFlyt: Active Vision Based Minimalist Structure-less Gap Detection For Quadrotor Flight](https://mlsanity.com/paper/1802.05330/) (2018)
- [A Mathematical Characterization of Minimally Sufficient Robot Brains](https://mlsanity.com/paper/2308.09041/) (2023)
- [Task-Driven Estimation and Control via Information Bottlenecks](https://mlsanity.com/paper/1809.07874/) (2018)
- [CodedVO: Coded Visual Odometry](https://mlsanity.com/paper/2407.18240/) (2024)
- [Joint Forward-Backward Visual Odometry for Stereo Cameras](https://mlsanity.com/paper/1912.10293/) (2019)
- [Visual Gyroscope: Combination of Deep Learning Features and Direct Alignment for Panoramic Stabilization](https://mlsanity.com/paper/2402.01461/) (2024)
- [All Eyes, no IMU: Learning Flight Attitude from Vision Alone](https://mlsanity.com/paper/2507.11302/) (2025)
- [TinyDEVO: Deep Event-based Visual Odometry on Ultra-low-power Multi-core Microcontrollers](https://mlsanity.com/paper/2604.08060/) (2026)

## Abstract (arXiv)

Tiny robots have limited computation and memory, yet visual navigation systems often maintain more state than a task requires. We ask whether persistent memory can instead be shaped by the task. We present RingNav, a (10.6)k--parameter visual heading estimator that constrains its memory to the circular manifold (S1). RingNav learns only the turn between consecutive images, while heading is composed directly on the circle. On the TartanAir Visual SLAM Challenge, RingNav reduces mean absolute turn error by (27%) and accumulated heading error over 4 sec by (15%) relative to a similarly sized learned-memory model. The structured update also gives exactly zero turn for identical frames and exact cancellation under sequence reversal. Without fine-tuning, RingNav transfers to real-world drone experiments and continues estimating heading under severe visual degradation. RingNav runs at 27.3Hz on Raspberry Pi Zero 2W and can be deployed on an ultra-low power GAP8 processor at 33.4Hz.