Saved in:
Bibliographic Details
Main Authors: Ji, Zihe, Lin, Huangxuan, Gao, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.15096
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918062251311104
author Ji, Zihe
Lin, Huangxuan
Gao, Yue
author_facet Ji, Zihe
Lin, Huangxuan
Gao, Yue
contents We present DyNaVLM, an end-to-end vision-language navigation framework using Vision-Language Models (VLM). In contrast to prior methods constrained by fixed angular or distance intervals, our system empowers agents to freely select navigation targets via visual-language reasoning. At its core lies a self-refining graph memory that 1) stores object locations as executable topological relations, 2) enables cross-robot memory sharing through distributed graph updates, and 3) enhances VLM's decision-making via retrieval augmentation. Operating without task-specific training or fine-tuning, DyNaVLM demonstrates high performance on GOAT and ObjectNav benchmarks. Real-world tests further validate its robustness and generalization. The system's three innovations: dynamic action space formulation, collaborative graph memory, and training-free deployment, establish a new paradigm for scalable embodied robot, bridging the gap between discrete VLN tasks and continuous real-world navigation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15096
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory
Ji, Zihe
Lin, Huangxuan
Gao, Yue
Robotics
We present DyNaVLM, an end-to-end vision-language navigation framework using Vision-Language Models (VLM). In contrast to prior methods constrained by fixed angular or distance intervals, our system empowers agents to freely select navigation targets via visual-language reasoning. At its core lies a self-refining graph memory that 1) stores object locations as executable topological relations, 2) enables cross-robot memory sharing through distributed graph updates, and 3) enhances VLM's decision-making via retrieval augmentation. Operating without task-specific training or fine-tuning, DyNaVLM demonstrates high performance on GOAT and ObjectNav benchmarks. Real-world tests further validate its robustness and generalization. The system's three innovations: dynamic action space formulation, collaborative graph memory, and training-free deployment, establish a new paradigm for scalable embodied robot, bridging the gap between discrete VLN tasks and continuous real-world navigation.
title DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory
topic Robotics
url https://arxiv.org/abs/2506.15096