Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Weiye, Zhang, Zekai, Wang, Xiangchen, Pan, Hewei, Wang, Teng, Geng, Tiantian, Xu, Rongtao, Zheng, Feng
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.18188
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911517158408192
author Zhu, Weiye
Zhang, Zekai
Wang, Xiangchen
Pan, Hewei
Wang, Teng
Geng, Tiantian
Xu, Rongtao
Zheng, Feng
author_facet Zhu, Weiye
Zhang, Zekai
Wang, Xiangchen
Pan, Hewei
Wang, Teng
Geng, Tiantian
Xu, Rongtao
Zheng, Feng
contents Vision-and-Language Navigation (VLN) requires agents to interpret natural language instructions and act coherently in visually rich environments. However, most existing methods rely on reactive state-action mappings without explicitly action-grounded visual dynamics modeling. Lacking awareness of how actions transform subsequent visual observations, agents cannot plan actions rationally, leading to unstable behaviors, weak generalization, and cumulative error along trajectory. To address these issues, we introduce \textsc{NaVIDA} (\textbf{Nav}igation with \textbf{I}nverse \textbf{D}ynamics \textbf{A}ugmentation), a lightweight VLN framework that incorporates inverse dynamics supervision (IDS) as an explicit objective to embed action-grounded visual dynamics into policy learning. By jointly optimizing this visual dynamics with instruction-conditioned action prediction in a shared representation and action space, \textsc{NaVIDA} provides additional structured supervision that regularizes learning and leads to more stable and consistent navigation. To structure this supervision and extend the effective planning range, \textsc{NaVIDA} employs hierarchical probabilistic action chunking (HPAC), which organizes trajectories into multi-step chunks and provides discriminative, longer-range visual-change cues. Extensive experiments show that \textsc{NaVIDA} achieves superior navigation performance compared to state-of-the-art methods with fewer parameters (3B vs. 8B). Real-world robot evaluations further validate the practical feasibility and effectiveness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18188
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle \textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation
Zhu, Weiye
Zhang, Zekai
Wang, Xiangchen
Pan, Hewei
Wang, Teng
Geng, Tiantian
Xu, Rongtao
Zheng, Feng
Computer Vision and Pattern Recognition
Artificial Intelligence
Vision-and-Language Navigation (VLN) requires agents to interpret natural language instructions and act coherently in visually rich environments. However, most existing methods rely on reactive state-action mappings without explicitly action-grounded visual dynamics modeling. Lacking awareness of how actions transform subsequent visual observations, agents cannot plan actions rationally, leading to unstable behaviors, weak generalization, and cumulative error along trajectory. To address these issues, we introduce \textsc{NaVIDA} (\textbf{Nav}igation with \textbf{I}nverse \textbf{D}ynamics \textbf{A}ugmentation), a lightweight VLN framework that incorporates inverse dynamics supervision (IDS) as an explicit objective to embed action-grounded visual dynamics into policy learning. By jointly optimizing this visual dynamics with instruction-conditioned action prediction in a shared representation and action space, \textsc{NaVIDA} provides additional structured supervision that regularizes learning and leads to more stable and consistent navigation. To structure this supervision and extend the effective planning range, \textsc{NaVIDA} employs hierarchical probabilistic action chunking (HPAC), which organizes trajectories into multi-step chunks and provides discriminative, longer-range visual-change cues. Extensive experiments show that \textsc{NaVIDA} achieves superior navigation performance compared to state-of-the-art methods with fewer parameters (3B vs. 8B). Real-world robot evaluations further validate the practical feasibility and effectiveness of our approach.
title \textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.18188