SEDualVLN: A Spatially-Enhanced Dual-System Framework for Vision-Language Navigation

arXiv:2605.17249 · cs.RO · Submitted 2026-05-17 · Read on arXiv

cs.RO

Submitted: 2026-05-17

Updated: 2026-10-11

Code: https://github.com/kim-os/SEDualVLN

Terminology

• Vision-Language Navigation — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Multimodal Large Language Model — 1× in this paper
• Vision-Language Model — 1× in this paper
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes

Sources

• LLaVA-Video: Video Instruction Tuning With Synthetic Data
• Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
• NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
• End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering
• StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
• JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
• DyGeoVLN: Infusing Dynamic Geometry Foundation Model into Vision-Language Navigation
• P$^{3}$Nav: End-to-End Perception, Prediction and Planning for Vision-and-Language Navigation
• Spatial-VLN: Zero-Shot Vision-and-Language Navigation With Explicit Spatial Perception and Exploration
• SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation
• HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System
• InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment
• Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
• Geometric Context Transformer for Streaming 3D Reconstruction
• Qwen2.5-Coder Technical Report

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies