LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ning, Yuwei, Zhao, Ganlong, Qin, Yipeng, Liu, Si, Liu, Yang, Lin, Liang, Li, Guanbin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913044997603328
author Ning, Yuwei
Zhao, Ganlong
Qin, Yipeng
Liu, Si
Liu, Yang
Lin, Liang
Li, Guanbin
author_facet Ning, Yuwei
Zhao, Ganlong
Qin, Yipeng
Liu, Si
Liu, Yang
Lin, Liang
Li, Guanbin
contents Aerial Vision-and-Language Navigation (Aerial VLN) enables unmanned aerial vehicles (UAVs) to follow natural language instructions and navigate complex urban environments. While recent advances have achieved progress through large-scale memory graphs and lookahead path planning, they remain limited by shallow instruction understanding and high computational cost. In particular, existing methods rely primarily on landmark descriptions, overlooking directional cues "a key source of spatial context in human navigation". In this work, we propose LookasideVLN, a new paradigm that exploits directional cues in natural language to achieve both more accurate spatial reasoning and greater computational efficiency. LookasideVLN comprises three core components: (1) an Egocentric Lookaside Graph (ELG) that dynamically encodes instruction-relevant landmarks and their directional relationships, (2) a Spatial Landmark Knowledge Base (SLKB) that provides lightweight memory retrieval from prior navigation experiences, and (3) a Lookaside MLLM Navigation Agent that aligns multimodal information from user instructions, visual observations, and landmark-direction information from ELG for path planning. Extensive experiments show that LookasideVLN significantly outperforms the state-of-the-art CityNavAgent, even with a single-level lookahead, demonstrating that leveraging directional cues is a powerful yet efficient strategy for Aerial VLN.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17190
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation
Ning, Yuwei
Zhao, Ganlong
Qin, Yipeng
Liu, Si
Liu, Yang
Lin, Liang
Li, Guanbin
Computer Vision and Pattern Recognition
Aerial Vision-and-Language Navigation (Aerial VLN) enables unmanned aerial vehicles (UAVs) to follow natural language instructions and navigate complex urban environments. While recent advances have achieved progress through large-scale memory graphs and lookahead path planning, they remain limited by shallow instruction understanding and high computational cost. In particular, existing methods rely primarily on landmark descriptions, overlooking directional cues "a key source of spatial context in human navigation". In this work, we propose LookasideVLN, a new paradigm that exploits directional cues in natural language to achieve both more accurate spatial reasoning and greater computational efficiency. LookasideVLN comprises three core components: (1) an Egocentric Lookaside Graph (ELG) that dynamically encodes instruction-relevant landmarks and their directional relationships, (2) a Spatial Landmark Knowledge Base (SLKB) that provides lightweight memory retrieval from prior navigation experiences, and (3) a Lookaside MLLM Navigation Agent that aligns multimodal information from user instructions, visual observations, and landmark-direction information from ELG for path planning. Extensive experiments show that LookasideVLN significantly outperforms the state-of-the-art CityNavAgent, even with a single-level lookahead, demonstrating that leveraging directional cues is a powerful yet efficient strategy for Aerial VLN.
title LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.17190