# Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments

arXiv: https://arxiv.org/abs/2605.28442 · HTML: https://mlsanity.com/paper/2605.28442/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 26 of 26)

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [BADGR: An Autonomous Self-Supervised Learning-Based Navigation System](https://mlsanity.com/paper/2002.05700/) (2020)
- [FAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter](https://mlsanity.com/paper/2010.08196/) (2020)
- [Fast Traversability Estimation for Wild Visual Navigation](https://mlsanity.com/paper/2305.08510/) (2023)
- [Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning](https://mlsanity.com/paper/1912.03227/) (2019)
- [WayFAST: Navigation with Predictive Traversability in the Field](https://mlsanity.com/paper/2203.12071/) (2022)
- [V-STRONG: Visual Self-Supervised Traversability Learning for Off-road Navigation](https://mlsanity.com/paper/2312.16016/) (2023)
- [Universal Time-Series Representation Learning: A Survey](https://mlsanity.com/paper/2401.03717/) (2024)
- [How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversability](https://mlsanity.com/paper/2209.10788/) (2022)
- [EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy](https://mlsanity.com/paper/2311.06234/) (2023)
- [STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience](https://mlsanity.com/paper/2309.15302/) (2023)
- [WayFASTER: a Self-Supervised Traversability Prediction for Increased Navigation Awareness](https://mlsanity.com/paper/2402.00683/) (2024)
- [Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perception](https://mlsanity.com/paper/2407.18145/) (2024)
- [Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptation](https://mlsanity.com/paper/2210.09739/) (2022)
- [INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields](https://mlsanity.com/paper/2303.18101/) (2023)
- [SALON: Self-supervised Adaptive Learning for Off-road Navigation](https://mlsanity.com/paper/2412.07826/) (2024)
- [ProNav: Proprioceptive Traversability Estimation for Legged Robot Navigation in Outdoor Environments](https://mlsanity.com/paper/2307.09754/) (2023)
- [AMCO: Adaptive Multimodal Coupling of Vision and Proprioception for Quadruped Robot Navigation in Outdoor Environments](https://mlsanity.com/paper/2403.13235/) (2024)
- [IMOST: Incremental Memory Mechanism with Online Self-Supervision for Continual Traversability Learning](https://mlsanity.com/paper/2409.14070/) (2024)
- [CROSS-GAiT: Cross-Attention-Based Multimodal Representation Fusion for Parametric Gait Adaptation in Complex Terrains](https://mlsanity.com/paper/2409.17262/) (2024)
- [TerraPN: Unstructured Terrain Navigation using Online Self-Supervised Learning](https://mlsanity.com/paper/2202.12873/) (2022)
- [Deep Probabilistic Traversability with Test-time Adaptation for Uncertainty-aware Planetary Rover Navigation](https://mlsanity.com/paper/2409.00641/) (2024)

## Built on by (most cited first, 1 of 1)

- [Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking](https://mlsanity.com/paper/2609.23673/) (2026)

## Abstract (arXiv)

Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation behavior toward safe and efficient trajectories. Existing approaches either rely on handcrafted proprioceptive traversability scores, limiting robot-agnosticism, or cluster prior data, preventing online learning. Moreover, many continual learning methods incur substantial memory and computational costs, hindering onboard deployment. We introduce COTRATE, an online learning framework for continuous traversability estimation from multimodal, unlabeled robot experience. Our method first infers robust traversability scores using a robot-agnostic, learning-based online terrain assessment module operating on proprioceptiveand inertial signals. These scores then supervise a visual traversability network through a novel alignment loss that associates visual embeddings with online terrain assessments. To mitigate forgetting during continual learning with minimal overhead, we propose a diversity-aware feature selection strategythat preserves performance using a compact replay memory. We further show that the learned traversability representation supports knowledge transfer across different robot platforms with different locomotion kinematics. We evaluate COTRATE on a dataset of ≈ 50,000 images collected with two robotic platforms across 11 outdoor terrains, and benchmark it on navigation tasks in three representative outdoor environments. We make the dataset, code, and trained models publicly available.