SkeNa: Learning to Navigate Unseen Environments Based on Abstract Hand-Drawn Maps

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Haojun, Xiang, Jiaqi, Wei, Wu, Chen, Jinyu, Zhong, Linqing, Huang, Linjiang, Yang, Hongyu, Liu, Si
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909722143096832
author Xu, Haojun
Xiang, Jiaqi
Wei, Wu
Chen, Jinyu
Zhong, Linqing
Huang, Linjiang
Yang, Hongyu
Liu, Si
author_facet Xu, Haojun
Xiang, Jiaqi
Wei, Wu
Chen, Jinyu
Zhong, Linqing
Huang, Linjiang
Yang, Hongyu
Liu, Si
contents A typical human strategy for giving navigation guidance is to sketch route maps based on the environmental layout. Inspired by this, we introduce Sketch map-based visual Navigation (SkeNa), an embodied navigation task in which an agent must reach a goal in an unseen environment using only a hand-drawn sketch map as guidance. To support research for SkeNa, we present a large-scale dataset named SoR, comprising 54k trajectory and sketch map pairs across 71 indoor scenes. In SoR, we introduce two navigation validation sets with varying levels of abstraction in hand-drawn sketches, categorized based on their preservation of spatial scales in the environment, to facilitate future research. To construct SoR, we develop an automated sketch-generation pipeline that efficiently converts floor plans into hand-drawn representations. To solve SkeNa, we propose SkeNavigator, a navigation framework that aligns visual observations with hand-drawn maps to estimate navigation targets. It employs a Ray-based Map Descriptor (RMD) to enhance sketch map valid feature representation using equidistant sampling points and boundary distances. To improve alignment with visual observations, a Dual-Map Aligned Goal Predictor (DAGP) leverages the correspondence between sketch map features and on-site constructed exploration map features to predict goal position and guide navigation. SkeNavigator outperforms prior floor plan navigation methods by a large margin, improving SPL on the high-abstract validation set by 105% relatively. Our code and dataset will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03053
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SkeNa: Learning to Navigate Unseen Environments Based on Abstract Hand-Drawn Maps
Xu, Haojun
Xiang, Jiaqi
Wei, Wu
Chen, Jinyu
Zhong, Linqing
Huang, Linjiang
Yang, Hongyu
Liu, Si
Robotics
Artificial Intelligence
A typical human strategy for giving navigation guidance is to sketch route maps based on the environmental layout. Inspired by this, we introduce Sketch map-based visual Navigation (SkeNa), an embodied navigation task in which an agent must reach a goal in an unseen environment using only a hand-drawn sketch map as guidance. To support research for SkeNa, we present a large-scale dataset named SoR, comprising 54k trajectory and sketch map pairs across 71 indoor scenes. In SoR, we introduce two navigation validation sets with varying levels of abstraction in hand-drawn sketches, categorized based on their preservation of spatial scales in the environment, to facilitate future research. To construct SoR, we develop an automated sketch-generation pipeline that efficiently converts floor plans into hand-drawn representations. To solve SkeNa, we propose SkeNavigator, a navigation framework that aligns visual observations with hand-drawn maps to estimate navigation targets. It employs a Ray-based Map Descriptor (RMD) to enhance sketch map valid feature representation using equidistant sampling points and boundary distances. To improve alignment with visual observations, a Dual-Map Aligned Goal Predictor (DAGP) leverages the correspondence between sketch map features and on-site constructed exploration map features to predict goal position and guide navigation. SkeNavigator outperforms prior floor plan navigation methods by a large margin, improving SPL on the high-abstract validation set by 105% relatively. Our code and dataset will be released.
title SkeNa: Learning to Navigate Unseen Environments Based on Abstract Hand-Drawn Maps
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2508.03053