mlsanityData to 14 Oct 2026

Fast Traversability Estimation for Wild Visual Navigation

arXiv 2305.08510 ↗First posted 15 May 2023cs.RO cs.CV cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes. In this work, we propose Wild Visual Navigation (WVN), an online self-supervised learning system for traversability estimation which uses only vision. The system is able to continuously adapt from a short human demonstration in the field. It leverages high-dimensional features from self-supervised visual transformer models, with an online scheme for supervision generation that runs in real-time on the robot. We demonstrate the advantages of our approach with experiments and ablation studies in challenging environments in forests, parks, and grasslands. Our system is able to bootstrap the traversable terrain segmentation in less than 5 min of in-field training time, enabling the robot to navigate in complex outdoor terrains - negotiating obstacles in high grass as well as a 1.4 km footpath following. While our experiments were executed with a quadruped robot, ANYmal, the approach presented can generalize to any ground robot.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). Builds on 20 of its 43 references that are in the map. First posted on arXiv 15 May 2023.

Builds on

20 of 43 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  5. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  6. 2020BADGR: An Autonomous Self-Supervised Learning-Based Navigation Systemcited by 102
  7. 2022Elevation Mapping for Locomotion and Navigation using GPUcited by 43
  8. 2019Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learningcited by 38
  9. 2020Safe Robot Navigation via Multi-Modal Anomaly Detectioncited by 34
  10. 2022WayFAST: Navigation with Predictive Traversability in the Fieldcited by 32
  11. 2022Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environmentscited by 28
  12. 2021STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigationcited by 27
8 more
  1. 2021Autonomous Exploration Development Environment and the Planning Algorithmscited by 27
  2. 2022GrASPE: Graph based Multimodal Fusion for Robot Navigation in Unstructured Outdoor Environmentscited by 25
  3. 2022ScaTE: A Scalable Framework for Self-Supervised Traversability Estimation in Unstructured Environmentscited by 21
  4. 2017Learning Ground Traversability from Simulationscited by 20
  5. 2021Heterogeneous Ground and Air Platforms, Homogeneous Sensing: Team CSIRO Data61's Approach to the DARPA Subterranean Challengecited by 18
  6. 2022Proactive Anomaly Detection for Robot Navigation with Multi-Sensor Fusioncited by 15
  7. 2022An Efficient Locally Reactive Controller for Safe Navigation in Visual Teach and Repeat Missionscited by 14
  8. 2022Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 13; 2025: 10; 2026: 11.

44 papers.

Sort:

By area:

  1. 2024Navigation World Modelscited by 272
  2. 2024RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Drivingcited by 26
  3. 2023Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-Endcited by 23
  4. 2023EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomycited by 21
  5. 2024Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervisioncited by 17
  6. 2023Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learningcited by 14
  7. 2025Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresightcited by 14
  8. 2024DTG : Diffusion-based Trajectory Generation for Mapless Global Navigationcited by 13
  9. 2023Learning Vision-based Pursuit-Evasion Robot Policiescited by 11
  10. 2023STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experiencecited by 11
  11. 2023MEM: Multi-Modal Elevation Mapping for Robotics and Learningcited by 11
  12. 2023Learning to See Physical Properties with Active Sensing Motor Policiescited by 10
32 more
  1. 2024Identifying Terrain Physical Parameters from Vision -- Towards Physical-Parameter-Aware Locomotion and Navigationcited by 10
  2. 2026Language-Conditioned World Modeling for Visual Navigationcited by 10
  3. 2024PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terraincited by 8
  4. 2023Wait, That Feels Familiar: Learning to Extrapolate Human Preferences for Preference Aligned Path Planningcited by 7
  5. 2025Imitation Learning from a Single Temporally Misaligned Videocited by 7
  6. 2025GeNIE: A Generalizable Navigation System for In-the-Wild Environmentscited by 7
  7. 2023Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perceptioncited by 5
  8. 2024Learning Semantic Traversability with Egocentric Video and Automated Annotation Strategycited by 5
  9. 2024RoadRunner M&M -- Learning Multi-range Multi-resolution Traversability Maps for Autonomous Off-road Navigationcited by 5
  10. 2026NavWM: A Unified Navigation World Model for Foresight-Driven Planningcited by 5
  11. 2024ZSL-RPPO: Zero-Shot Learning for Quadrupedal Locomotion in Challenging Terrains using Recurrent Proximal Policy Optimizationcited by 4
  12. 2025Risk-Guided Diffusion: Toward Deploying Robot Foundation Models in Space, Where Failure Is Not An Optioncited by 3
  13. 2025ZeST: A VLM-based Zero-Shot Traversability Navigation for Unknown Environmentscited by 3
  14. 2026WildOS: Open-Vocabulary Object Search in the Wildcited by 3
  15. 2024TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimationcited by 2
  16. 2024IN-Sight: Interactive Navigation through Sightcited by 2
  17. 2024TE-NeXt: A LiDAR-Based 3D Sparse Convolutional Network for Traversability Estimationcited by 1
  18. 2025Holistic Fusion: Task- and Setup-Agnostic Robot Localization and State Estimation with Factor Graphscited by 1
  19. 2026Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environmentscited by 1
  20. 2023METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigationcited by 0
  21. 2024AdaCropFollow: Self-Supervised Online Adaptation for Visual Under-Canopy Navigationcited by 0
  22. 2025ADEPT: Adaptive Diffusion Environment for Policy Transfer Sim-to-Realcited by 0
  23. 2025Learning Smooth State-Dependent Traversability from Dense Point Cloudscited by 0
  24. 2025Scene-Agnostic Traversability Labeling and Estimation via a Multimodal Self-supervised Frameworkcited by 0
  25. 2025Mars Traversability Prediction: A Multi-modal Self-supervised Approach for Costmap Generationcited by 0
  26. 2026Trinity: Unifying Class-Agnostic Terrain and Semantic Segmentation for Unstructured Outdoor Environments by Leveraging Synthetic Datacited by 0
  27. 2026Sensor Configuration Matters: A Systematic Evaluation of Multimodal SLAM on Quadruped Robotscited by 0
  28. 2026Continual Learning for Traversability Prediction with Uncertainty-Aware Adaptationcited by 0
  29. 2026Feeling Terrain Before Crossing: World Models for Off-Road Navigationcited by 0
  30. 2026FLINT: Fast Lightweight Inference for Traversabilitycited by 0
  31. 2026From Language Priors to Field Adaptation: Preference Learning for Traversability Estimationcited by 0
  32. 2026From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Predictioncited by 0