Salvato in:
Dettagli Bibliografici
Autori principali: Yao, Xuan, Gao, Junyu, Xu, Changsheng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.23468
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913951918325760
author Yao, Xuan
Gao, Junyu
Xu, Changsheng
author_facet Yao, Xuan
Gao, Junyu
Xu, Changsheng
contents Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instructions. Current approaches often struggle with generalizing to novel environments and adapting to ongoing changes during navigation. Inspired by human cognition, we present NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making in VLN-CE tasks. NavMorph employs compact latent representations to model environmental dynamics, equipping agents with foresight for adaptive planning and policy refinement. By integrating a novel Contextual Evolution Memory, NavMorph leverages scene-contextual information to support effective navigation while maintaining online adaptability. Extensive experiments demonstrate that our method achieves notable performance improvements on popular VLN-CE benchmarks. Code is available at https://github.com/Feliciaxyao/NavMorph.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23468
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
Yao, Xuan
Gao, Junyu
Xu, Changsheng
Computer Vision and Pattern Recognition
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instructions. Current approaches often struggle with generalizing to novel environments and adapting to ongoing changes during navigation. Inspired by human cognition, we present NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making in VLN-CE tasks. NavMorph employs compact latent representations to model environmental dynamics, equipping agents with foresight for adaptive planning and policy refinement. By integrating a novel Contextual Evolution Memory, NavMorph leverages scene-contextual information to support effective navigation while maintaining online adaptability. Extensive experiments demonstrate that our method achieves notable performance improvements on popular VLN-CE benchmarks. Code is available at https://github.com/Feliciaxyao/NavMorph.
title NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.23468