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

• URL: http://arxiv.org/abs/2605.17249v1
• Date: Sun, 17 May 2026 04:12:56 GMT
• Title: SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation
• Abstract summary: We introduce SEDualVLN, a spatially-enhanced dual-system Vision-Language Navigation framework.<n>System 1 is a VLM model enhanced with both global and local spatial awareness, used for action generation.<n>System 2 integrates a general MLLM with a mapping module, wherein the MLLM plans waypoints by leveraging top-down views of the real-time 3D map.
• Score: 19.9336847486232
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Navigation (VLN) approaches have currently followed two primary paradigms: the end-to-end Vision-Language Model (VLM) policy fine-tuned on navigation trajectories to directly predict actions, and the zero-shot modular pipeline integrating pre-trained Multimodal Large Language Model (MLLM) for training-free generalization to unseen environments. However, end-to-end methods struggle with long-horizon navigation and lack dynamic reasoning, whereas zero-shot methods are constrained by limited spatial grounding for reliable planning and also require substantial reasoning time. To bridge this gap, we introduce SEDualVLN, a spatially-enhanced dual-system VLN framework. System 1 is a VLM model enhanced with both global and local spatial awareness, used for action generation. System 2 integrates a general MLLM with a mapping module, wherein the MLLM plans waypoints by leveraging top-down views of the real-time 3D map alongside streams of rendered path images. Both systems leverage different forms of spatial enhancement to cultivate the agent's sense of direction in VLN tasks. Ultimately, they cooperate to complete the navigation task through a fast-slow coordinated approach. SEDualVLN achieves state-of-the-art performance on VLN-CE benchmarks, and further ablation studies demonstrate the effectiveness of each system and module.

Related papers

• Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation [68.02899606570223]
  We propose TAMP-Nav, a unified framework for efficient embodied navigation.<n>First, we introduce a Pixel-to-3D Action Formulation (Point) that reformulates navigation into 2D visual coordinates.<n>Second, we propose an integrated Selective Reasoning and Anchor-Trajectory Memory mechanism (Think and Memorize)
  arXiv  Detail & Related papers  (2026-08-18T08:37:08Z)
• FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation [33.92221208368759]
  Vision-Language Navigation (VLN) is an autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs.<n>Existing methods suffer from structural misalignment between global multimodal understanding and sequential action generation.<n>We propose FSD-VLN, a fast-slow dual-system architecture disentangling semantic reasoning and low-altitude flight command generation.
  arXiv  Detail & Related papers  (2026-07-09T11:17:04Z)
• DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA [72.9197085473598]
  DIAL is a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck.<n>A VLM-based System-2 performs latent world modeling by latent visual foresight within the VLM's native feature space.<n>A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions.
  arXiv  Detail & Related papers  (2026-03-31T15:02:27Z)
• AgentVLN: Towards Agentic Vision-and-Language Navigation [78.739525400071]
  Vision-and-Language Navigation (VLN) requires an embodied agent to ground complex natural-language instructions into long-horizon navigation in unseen environments.<n>In this paper, we propose AgentVLN, a novel and efficient embodied navigation framework that can be deployed on edge computing platforms.
  arXiv  Detail & Related papers  (2026-03-18T12:43:47Z)
• Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation [45.54638103934175]
  We propose DualVLN, a vision-language navigation system that integrates high-level reasoning with low-level action execution.<n>System 1 "moves fast" by leveraging both explicit pixel goals and latent features from System 2 to generate smooth and accurate trajectories.<n>System outperforms prior methods across all VLN benchmarks and real-world experiments demonstrate robust long-horizon planning and real-time adaptability.
  arXiv  Detail & Related papers  (2025-12-09T02:29:36Z)
• Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation [16.632191523127865]
  Fast-SmartWay is an end-to-end zero-shot VLN-CE framework that eliminates the need for panoramic views and waypoint predictors.<n>Our approach uses only three frontal RGB-D images combined with natural language instructions, enabling MLLMs to directly predict actions.
  arXiv  Detail & Related papers  (2025-11-02T13:21:54Z)
• Following Route Instructions using Large Vision-Language Models: A Comparison between Low-level and Panoramic Action Spaces [2.2406151150434894]
  Vision-and-Language Navigation (VLN) enables autonomous robots to navigate unfamiliar environments by following natural language instructions.<n>Current VLN systems rely on models specifically designed and optimized for navigation, leaving the potential of off-the-shelf LVLMs underexplored.<n>This paper investigates whether off-the-shelf LVLMs can effectively support VLN tasks and whether such models can support both low-level and panoramic action paradigms.
  arXiv  Detail & Related papers  (2025-08-04T21:45:21Z)
• VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning [77.34267241692706]
  Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions.<n>We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions.
  arXiv  Detail & Related papers  (2025-06-20T17:59:59Z)
• BEVBert: Multimodal Map Pre-training for Language-guided Navigation [75.23388288113817]
  We propose a new map-based pre-training paradigm that is spatial-aware for use in vision-and-language navigation (VLN) We build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dependency in a global topological map. Based on the hybrid map, we devise a pre-training framework to learn a multimodal map representation, which enhances spatial-aware cross-modal reasoning thereby facilitating the language-guided navigation goal.
  arXiv  Detail & Related papers  (2022-12-08T16:27:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.