AwareVLN: Self-Awareness Reasoning for Vision-Language Navigation

Forum topic · 小凯 · 2026-05-25

Summary

AwareVLN is a new framework for Vision-Language Navigation (VLN) that equips navigation models with self-awareness reasoning, enabling agents to understand their own state and task progress in a fully end-to-end, data-driven manner. The paper addresses a gap in current state-of-the-art approaches that use vision-language models (VLMs) for end-to-end action prediction: these methods often lack an explicit, interpretable understanding of the relationships between the agent, the instruction, and the scene. While explicit scene-map construction for heuristic planning is intuitively appealing, it requires additional 3D sensors and hinders large-scale vision-language pretraining. AwareVLN introduces two key innovations: (1) a structural reasoning module that promotes spatial and task-oriented self-awareness, and (2) an automated data engine with progress partitioning for effective training. Experiments across multiple datasets in the Habitat simulator show that AwareVLN significantly outperforms prior state-of-the-art VLN methods. The paper (arXiv:2505.14487) is authored by Wenxuan Guo, Xiuwei Xu, and Yichen Liu in the computer vision field.

Paper Overview

Research Area: Computer Vision (CV) Authors: Wenxuan Guo, Xiuwei Xu, Yichen Liu Published: 2026-05-25 arXiv: 2505.14487

Abstract

Vision-Language Navigation (VLN) requires an agent to ground language instructions into its own embodiment within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of vision-language models (VLMs) for end-to-end action prediction, they often lack an explicit and interpretable understanding of the relationships between the agent, the instruction, and the scene. Conversely, explicitly constructing scene maps for heuristic planning is intuitively appealing, but relies on additional 3D sensors and hinders large-scale vision-language pretraining.

To bridge this gap, the authors propose AwareVLN, a new framework that equips navigation models with a self-awareness reasoning mechanism, enabling them to understand agent state and task progress in a fully end-to-end and data-driven manner.

Key Innovations

1. Structural reasoning module: promotes spatial and task-oriented self-awareness. 2. Automated data engine with progress partitioning: enables effective training.

Results

Extensive experiments on multiple datasets within the Habitat simulator demonstrate that AwareVLN significantly outperforms prior state-of-the-art Vision-Language Navigation methods.