SignNav: Leveraging Signage for Semantic Visual Navigation in Large-Scale Indoor Environments

Jian Sun; Yuming Huang; He Li; Shuqi Xiao; Shenyan Guo; Maani Ghaffari; Qingbiao Li; Chengzhong Xu

cs.ROMar 17, 2026

SignNav: Leveraging Signage for Semantic Visual Navigation in Large-Scale Indoor Environments

Authors: Jian Sun, Yuming Huang, He Li, Shuqi Xiao, Shenyan Guo, Maani Ghaffari, Qingbiao Li, Chengzhong Xu,

Organizations: Faculty of Science and Technology, University of Macau · Department of Robotics, University of Michigan

Abstract

Humans routinely leverage semantic hints provided by signage to navigate to destinations within novel Large-Scale Indoor (LSI) environments, such as hospitals and airport terminals. However, this capability remains underexplored within the field of embodied navigation. This paper introduces a novel embodied navigation task, SignNav, which requires the agent to interpret semantic hint from signage and reason about the subsequent action based on current observation. To facilitate research in this domain, we construct the LSI-Dataset for the training and evaluation of various SignNav agents. Dynamically changing semantic hints and sparse placement of signage in LSI environments present significant challenges to the SignNav task. To address these challenges, we propose the Spatial-Temporal Aware Transformer (START) model for end-to-end decision-making. The spatial-aware module grounds the semantic hint of signage into physical world, while the temporal-aware module captures long-range dependencies between historical states and current observation. Leveraging a two-stage training strategy with Dataset Aggregation (DAgger), our approach achieves state-of-the-art performance, recording an 80% Success Rate (SR) and 0.74 NDTW on val-unseen split. Real-world deployment further demonstrates the practicality of our method in physical environment without pre-built map.

Figures & tables

Fig. 1: Capital Region International Airport in Clinton County, Michigan . When humans first arrive at an airport terminal, they routinely leverage the semantic hints of signage to find their boarding gates. We formulate this problem as an embodied navigation task SignNav and build the LSI-Dataset to promote the solution of SignNav.

Fig. 2: An episode example in a hospital scene. The agent is required to make action decisions according to the semantic hints of signage (detected directional arrows) and finally arrive at the target location.

Fig. 3: The architecture of our Spatial-Temporal Aware Transformer (START) model for the SignNav task. START uses a spatial-aware module for grounding the semantic hint of sigange into egocentric observation, and a temporal-aware module for capturing long-range dependencies between the historical states and current observation.

Panel of Figure 4 — Fig. 4: Different action decisions under different circumstances. (a) different semantic hints at the same location; (b) the same semantic hints at different locations; (c) different semantic hints at different locations.

Fig. 5: One period in an episode that there is no visible semantic hints of signage. The agent still needs to make correct decisions when there is no visible semantic hint.

Fig. 6: Trajectories visualization of our method compared to baselines. The second row shows the first-person-view of agent as it navigates along the ground-truth trajectory.

Methods	Val-Seen			Val-Unseen
Methods	SR	NDTW	SDTW	SR	NDTW	SDTW
VLM-based	0.28	0.46	0.21	0.30	0.54	0.25
Rule-based [ 28 ]	0.51	0.65	0.42	0.67	0.73	0.56
ViNT [ 39 ]	0.76	0.71	0.64	0.68	0.69	0.57
START	0.90	0.80	0.76	0.80	0.74	0.67

TABLE I: Performance comparison with different baselines.

RMSE $(m)$	Navigation Distance $(m)$
RMSE $(m)$	40	80	120	160	200
Val-Seen	0.28	0.25	0.24	0.25	0.24
Val-Unseen	0.25	0.26	0.26	0.28	0.27

TABLE II: Trajectory error statistics at different distances.

Fig. 7: Real-world deployment of our method in an office building to find the “Lifts” leveraging signage.

Spa- Aware	Tem- Aware	Val-Seen			Val-Unseen
Spa- Aware	Tem- Aware	SR	NDTW	SDTW	SR	NDTW	SDTW
$\times$	$\checkmark$	0.60	0.67	0.50	0.39	0.57	0.33
$\checkmark$	$\times$	0.61	0.66	0.51	0.47	0.59	0.39
$\checkmark$	$\checkmark$	0.82	0.76	0.69	0.72	0.72	0.60

TABLE III: Ablation study for spatial and temporal-aware modules.

Panel of Figure 11 — Fig. 8: Attention map visualization both with the spatial-aware and temporal-aware modules in our START model. The darker the color, the greater the attention weight.

DAgger	Val-Seen			Val-Unseen
DAgger	SR	NDTW	SDTW	SR	NDTW	SDTW
$\times$	0.82	0.76	0.69	0.72	0.72	0.60
$\checkmark$	0.90	0.80	0.76	0.80	0.74	0.67

TABLE IV: Ablation study for the impact of training with DAgger.

RGB	Depth	Val-Seen			Val-Unseen
RGB	Depth	SR	NDTW	SDTW	SR	NDTW	SDTW
$\checkmark$	$\times$	0.67	0.70	0.56	0.59	0.68	0.49
$\times$	$\checkmark$	0.86	0.78	0.73	0.77	0.73	0.64
$\checkmark$	$\checkmark$	0.82	0.76	0.69	0.72	0.72	0.60

TABLE V: Ablation study for the impact of different modal inputs.

Spatiotemporal Transformers

See all 20 papers

SPAN-Nav: Generalized Spatial Awareness for Versatile Embodied Navigation
Mar 10, 2026Jiahang Liu, Tianyu Xu, Jiawei Chen +9Embodied Navigation Vision-Language Navigation
Peking University · Galbot · BAAI
SiGNgapore - An Interactive Dataset for Sign-based Visual Navigation
Oct 7, 2026Nicky Zimmerman, Joel Loo, Zishuo Wang +1Visual Robot Navigation Robot Navigation Benchmarks
National University of Singapore, SG
Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation
Aug 9, 2025Yue Hu, Junzhe Wu, Ruihan Xu +5World Model Learning Embodied Navigation
University of Michigan, Ann Arbor, US

Mar 10, 2026J/K move · Enter open · S save

SPAN-Nav: Generalized Spatial Awareness for Versatile Embodied Navigation

Jiahang Liu, Tianyu Xu, Jiawei Chen, Lu Yue+8

Peking University · Galbot · BAAI

Embodied Navigation Vision-Language Navigation Visual Spatial Reasoning VLMs for Robotics

Open paper AskPDF arXiv

Recent embodied navigation approaches leveraging Vision-Language Models (VLMs) demonstrate strong generalization in versatile Vision-Language Navigation (VLN). However, reliable path planning in complex environments remains challenging due to insufficient spatial awareness. In this work, we introduce SPAN-Nav, an end-to-end foundation model designed to infuse embodied navigation with universal 3D spatial awareness using RGB video streams. SPAN-Nav extracts spatial priors across diverse scenes through an occupancy prediction task on extensive indoor and outdoor environments. To mitigate the computational burden, we introduce a compact representation for spatial priors, finding that a single token is sufficient to encapsulate the coarse-grained cues essential for navigation tasks. Furthermore, inspired by the Chain-of-Thought (CoT) mechanism, SPAN-Nav utilizes this single spatial token to explicitly inject spatial cues into action reasoning through an end-to end framework. Leveraging multi-task co-training, SPAN-Nav captures task-adaptive cues from generalized spatial priors, enabling robust spatial awareness to generalize even to the task lacking explicit spatial supervision. To support comprehensive spatial learning, we present a massive dataset of 4.2 million occupancy annotations that covers both indoor and outdoor scenes across multi-type navigation tasks. SPAN-Nav achieves state-of-the-art performance across three benchmarks spanning diverse scenarios and varied navigation tasks. Finally, real-world experiments validate the robust generalization and practical reliability of our approach across complex physical scenarios.

Abstract

Spatiotemporal Transformers

Explore similar work

SPAN-Nav: Generalized Spatial Awareness for Versatile Embodied Navigation

SiGNgapore - An Interactive Dataset for Sign-based Visual Navigation

Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation