SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (22) · 18279-18287
DOI: 10.1609/aaai.v40i22.38891 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zebin Han und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task trajectory navigation guided by complex, long-horizon natural language instructions. Current vision-and-language navigation models exhibit significant performance degradation with such instructions, as information overload impairs the agent's ability to attend to observationally relevant details. To address this problem, we propose SeqWalker, a novel navigation model built on a hierarchical planning framework. Our SeqWalker features: (1) A High-Level Planner that dynamically selects global instructions into contextually relevant sub-instructions based on the agent's current visual observations, thus reducing cognitive load; (2) A Low-Level Planner incorporating an Exploration-Verification strategy that leverages the inherent logical structure of instructions for trajectory error correction. To evaluate SH-VLN performance, we also extend the IVLN dataset and establish a new benchmark. Extensive experiments are performed to demonstrate the effectiveness and superiority of SeqWalker.
Zitieren
APA
Han, Z., Wang, X., Liu, B., Lyu, Q., Shang, Z., Dong, J., Liu, L., & Han, Z. (2026). SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(22), 18279-18287. https://doi.org/10.1609/aaai.v40i22.38891
Vancouver
Han Z, Wang X, Liu B, Lyu Q, Shang Z, Dong J, et al. SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(22):18279-18287. doi:10.1609/aaai.v40i22.38891
BibTeX
@article{Han2026,
author = {Han, Zebin and Wang, Xudong and Liu, Baichen and Lyu, Qi and Shang, Zhenduo and Dong, Jiahua and Liu, Lianqing and Han, Zhi},
title = {SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {22},
pages = {18279--18287},
doi = {10.1609/aaai.v40i22.38891}
}
EUVIMED