AirLog: Store-Level Indoor Life Logging Made Easy

Zihui Yun; Jiaying Du; Yue Yu; Zhewei Liu; Zhen Xiang; Longfei Shangguan; Zhenlin An

cs.NISep 25, 2026

AirLog: Store-Level Indoor Life Logging Made Easy

Authors: Zihui Yun, Jiaying Du, Yue Yu, Zhewei Liu, Zhen Xiang, Longfei Shangguan, Zhenlin An

Organizations: University of Georgia Athens, Georgia, USA · University College London London, United Kingdom · University of Toronto Mississauga Mississauga, Ontario, Canada · University of Pittsburgh Pittsburgh, Pennsylvania, USA

Abstract

This paper presents AirLog, a smartphone-based life journaling system that automatically reconstructs users' store visits in shopping malls and summarizes them into human-readable journals. Unlike conventional indoor localization systems, AirLog avoids labor-intensive radio-map construction and dedicated wireless localization infrastructure and algorithm calibrations. Instead, it repurposes two cues already available in commercial spaces: semantic information exposed by ambient Wi-Fi SSIDs and indoor directory images. AirLog converts directory images into spatial maps and fuses Wi-Fi semantic anchors with inertial dead reckoning to recover store-level trajectories, which are then summarized into journals by an LLM. Such store-level life logs can support applications such as personal memory recall, activity reflection, and automated diary generation without requiring users to manually record where they have been. We implement AirLog on commodity smartphones and evaluate it on both a large-scale public dataset and a self-collected dataset. The results demonstrate that AirLog substantially improves store-level region recovery, semantic matching, trajectory reconstruction, and journal quality over existing baselines. A human evaluation further shows that the generated journals are coherent and faithful to users' visits.

Figures & tables

Figure 1. AirLog turns passive smartphone sensing into a store-level indoor life log. (A) While the user visits a shopping mall, the smartphone passively collects Wi-Fi scans and inertial measurements, and a publicly available floor-plan image is used as spatial context. (B) AirLog reconstructs the store-level trajectory—what stores were visited, in what order, and for how long—and summarizes it into a human-readable journal. (C) The life log is queryable: users can ask retrospective questions, such as where they went for lunch after visiting a specific store.

Figure 2. From general daily life logging to store-level indoor life journaling. AutoLife captures coarse multimodal context, while AirLog uses structured indoor maps and map-constrained multi-agent reasoning to reconstruct store-level trajectories.

Figure 3. AirLog overview. AirLog decomposes life logging into three structured layers: (1) Labeled Region Map Construction: a geometry-first parser converts an indoor directory image into a labeled region map serialized as GeoJSON. (2) Trajectory Reconstruction: a trajectory agent grounds sensor data and Wi-Fi semantics using downstream map constraints to infer store-level movement. (3) Journal Generation: a journal agent summarizes the validated trajectory into a third-person life journal.

Figure 4. From public maps to labeled region maps. (a) The public map provides venue-level context but lacks floor-level region geometry. (b) The floor-plan image contains the annotated regions and readable labels. (c) SAM 3 absorbs background structures and merges adjacent regions. (d) Color Filling is distracted by icons and other visual structures. (e) Boundary Detection extracts text and noise as candidate boundaries. (f) AirLog more closely recovers the annotated region geometry and labels. This example is qualitative; aggregate results appear in Table 1 .

Figure 5. Geometry-first map-parsing pipeline. From (a) an input floor-plan crop, AirLog generates (b) a clean region mask, performs (c) mask alignment, and extracts (d) region polygons. Each polygon produces (e) a polygon-masked crop for (f) the per-region semantic subagent. The returned label set is written directly to its source feature, producing (g) a labeled region map in GeoJSON. The pipeline first recovers region polygons from a generated and aligned clean mask, then invokes the per-region semantic subagent on one polygon-masked crop at a time and writes each label set directly to its source GeoJSON feature.

Figure 6. Trajectory Reconstruction in AirLog . The framework organizes three complementary contexts for indoor trajectory recovery: Wi-Fi Semantic Agent derives semantic location context, Motion Agent derives motion context, and Map Context Agent derives GeoJSON map constraints. The Context Fusion & Review Agent integrates these inputs and invokes structured inference to recover a geometrically consistent, store-level trajectory.

Figure 7. LLM-based semantic anchoring pipeline. Wi-Fi RSSI observations, spatial context, and POI context are combined into a structured prompt, producing multi-label POI hypotheses with confidence scores.

Figure 8. Semantic-priority Viterbi fusion. Wi-Fi semantic anchors score where the user is likely to be, PDR motion primitives score how the user could move, and the GeoJSON graph restricts the search to physically walkable transitions. The decoder first estimates a globally consistent trajectory, which is then reviewed by the multimodal feedback agent.

Figure 9. Workflow of Diary Generation. The reconstructed trajectory is aggregated into store-level visits by a behavior inference module (A). A motion calibration module (B) then refines each activity label using PDR geometry and location context. Finally, a diary agent (C) synthesizes the calibrated behavior sequence into a third-person Life Journal.

Method	Area F1 $\uparrow$	Region Purity $\uparrow$	Matched Label F1 $\uparrow$
Color Filling	0.277	0.510	0.523
Su et al.-style Boundary Detection	0.144	0.468	0.506
SAM 3	0.037	0.306	0.155
AirLog w/o semantic subagent	0.705	0.767	0.734
AirLog w/ semantic subagent	0.705	0.767	0.814

Table 1. Map-parsing results on the complete benchmark. Higher is better. The two AirLog rows share identical region geometry and differ only in semantic-labeling configuration.

Model	Input	Calls	Tokens (I/O)	Time (s)	Label F1
GPT-5.5	Full map	24/24	127.4k/137.0k	1,984.0	0.734
GPT-4o	Region crop	1,920/1,927	524.2k/24.6k	1,815.9	0.814

Table 2. Semantic labeling comparison. The GPT-4o per-region run contains 1,920 completed semantic records from 1,927 application attempts; all seven extra attempts were recovered by retries and no record was excluded.

Figure 12. Trajectory reconstruction evaluation.

Figure 13. Comparison of generated journals. Underlined italic denotes ground-truth POI names. Red denotes hallucinated or incorrect content. More details in the Appendix C .

Method	Hall. Rate $\downarrow$	chrF $\uparrow$	BERTScore $\uparrow$
Method	Hall. Rate $\downarrow$	chrF $\uparrow$	P	R	F1
SenLLM	0.667	0.331	0.263	0.403	0.330
AutoLife	0.636	0.381	0.363	0.458	0.409
AirLog	0.000	0.420	0.485	0.529	0.506

Table 3. Diary generation quality evaluation. Hall. Rate indicates the hallucination rate, chrF denotes the character F-score, and P , R , and F1 refer to the precision, recall, and F1 score of BERTScore.

Module	Input	Output	Cost (USD)	Calls
Spatial description	22.3k	1.2k	6.8 $\times 10^{-2}$ /hr	1 per floor
Wi-Fi semantic agent	118.7k	13.2k	4.3 $\times 10^{-1}$ /hr	$N_{w}$
Trajectory validation	62.8k	26.9k	4.3 $\times 10^{-1}$ /hr	1 per session
Behavior inference	1.9k	0.8k	1.3 $\times 10^{-2}$ /hr	1 per session
Journal generation	3.0k	1.3k	2.1 $\times 10^{-2}$ /hr	1 per session
Total per session	208.7k	43.4k	9.6 $\times 10^{-1}$ /hr	All modules

Table 4. Token usage and nominal estimated cost per session. Estimates use GPT-4o-equivalent rates of

2.50/1M input and

10.00/1M output tokens; they are not gateway invoices.

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Method	Region [email protected] $\uparrow$	[email protected] $\uparrow$
Color Filling	0.229	0.199
Boundary Detection / Su et al.	0.095	0.075
SAM 3	0.020	0.016
AirLog	0.590	0.475

Appendix

Table 5. Standard-metric sanity check on map geometry. Region [email protected] and [email protected] use one-to-one matching at IoU

\geq 0.5

and are macro-averaged across the 24 maps.

Panel of Figure 17 — Figure 17. Interface between map parsing and trajectory fusion. The labeled GeoJSON region map produced in Section 4 is converted by a separate deterministic stage into the corridor mask and navigability graph consumed in Section 5 . These artifacts are not parser outputs and are not included in the map-parsing metrics. Two visualizations show a corridor mask with region targets and the navigability graph derived later for trajectory fusion.

Figure 18. Exact-region OCR failures. PaddleOCR reads (a) a visible vertical HMV crop as AWH and (b) O2 as 02 . Two isolated region crops show an HMV-to-AWH orientation error and an O2-to-02 glyph-confusion error.

Figure 19. Two map-parsing interface failures. (a) A cached full-map GPT-5.5 result recognizes VOGUE but places its coordinate in the adjacent UBERFONE polygon; an exact-region input removes this binding step. (b) For one Crew -associated component, the predicted polygon removes the readable word from the masked crop, leaving no readable evidence for the semantic subagent. The upper panel contrasts a misplaced VOGUE coordinate with an exact-region crop. The lower panel shows a predicted polygon excluding Crew, followed by a text-free masked crop and an empty semantic result.

Metric	Hong Kong	Beijing	Shanghai	Shenzhen	Dalian	Nanjing	Total
Active hours (h)	59.3	5.8	208.4	225.5	2.6	101.3	603.0
GPS points	157,360	2,137	277,356	319,865	6,696	168,041	931,455
Wi-Fi observations	260,394	2,711	25,798	45,801	10,391	29,472	374,567
Unique SSIDs (raw)	21,303	984	1,730	2,125	1,604	1,274	29,020
Unique BSSIDs (raw)	56,615	1,742	2,541	3,199	2,832	1,922	68,851
Avg. SSIDs per scan	81.0	46.7	3.0	5.9	48.8	6.2	59.4

Appendix

Table 6. Dataset statistics across six cities.

Panel of Figure 20 — Figure 20. Representative Wi-Fi collection context. The density maps summarize two urban collection areas, while the Hong Kong panel provides a session-level view of mobility coverage.

Range	Cosine (Char)	Cosine (Word)	Cosine (TF-IDF)
0.0	9,731	184,841	184,871
0.0–0.2	33,454	3	3
0.2–0.4	72,318	131	65
0.4–0.6	54,474	137 (34.3%)	100 (9.0%)
0.6–0.8	14,516	17 (58.8%)	61 (44.3%)
0.8–1.0	647 (52.2%)	11 (100%)	40 (90.0%)

Appendix

Table 7. Number of SSID–POI pairs by similarity range and precision. Precision is computed over manually annotated same-store labels.

Wi-Fi SSID	POI	Best Sim.
SKH-SchoolDevice	SKH Holy Carpenter Church	0.693
Beauty	A Boutea	0.833
MNSGUEST	Monster Sushi	0.820
a SKH-SchoolDevice : SKH is a dominant institutional prefix of the Hong Kong Sheng Kung Hui; “SchoolDevice” identifies a campus device network, pointing to an affiliated lodging facility rather than the church itself.
b Beauty : “A Boutea” is a beverage brand whose name superficially resembles “Beauty” in spelling; the SSID more plausibly belongs to a cosmetics or personal-care venue.
c MNSGUEST : MNS follows a typical three-letter property code convention; combined with its location in the Miramar cluster in Tsim Sha Tsui, the network is better attributed to Miramar Shopping Centre’s guest Wi-Fi than to a restaurant abbreviation.

Appendix

Table 8. Representative bad cases of Wi-Fi SSID–POI matching. String similarity algorithms fail where LLM semantic reasoning succeeds.

Panel of Figure 21 — Figure 21. RSSI ambiguity and spatial layout. The profiles and map show why semantic anchoring is formulated as soft multi-label inference rather than a deterministic nearest-signal decision.

Figure 22. Journal generation case 2: restaurant visit.

Figure 23. Journal generation case 3: shopping and dining visit.

Figure 24. Prompt template for spatial description generation from GeoJSON floor-plan features.

Figure 25. Prompt template for Wi-Fi semantic anchoring using SSID semantics and signal evidence.

Trajectory Inference

Trajectory inference reconstructs continuous paths and underlying dynamics from sparse, noisy, or incomplete observations.

See all 37 papers

SlugTrails: An Egocentric Benchmark for Floor Plan Localization in Large Buildings
Sep 17, 2026Yunqian Cheng, Roberto ManduchiFloor-Plan-Based Visual Localization Visual Place Recognition
Department of Computer Science and Engineering University of California, Santa Cruz Santa Cruz, CA, USA
LangLoc: "Tell Me What You See"
Jul 6, 2026Shaurya Kishore Panwar, Roham Zendehdel Nobari, Shirley Feng Yi Lau +4
ETH Zürich, Switzerland · University of Zürich, Switzerland · Microsoft +1
Evaluating Memory Capability in Continuous Lifelog Scenario
Apr 13, 2026Jianjie Zheng, Zhichen Liu, Zhanyu Shen +6LLM Memory Memory Agent Benchmarks
Southern University of Science and Technology · Shenzhen University · Shanghai Jiao Tong University +1

Sep 17, 2026J/K move · Enter open · S save

SlugTrails: An Egocentric Benchmark for Floor Plan Localization in Large Buildings

Yunqian Cheng, Roberto Manduchi

Department of Computer Science and Engineering University of California, Santa Cruz Santa Cruz, CA, USA

Floor-Plan-Based Visual Localization Visual Place Recognition Map-Based Localization

Open paper AskPDF arXiv

Floor-plan-based indoor visual localization enables infrastructure-free positioning, but most methods are developed and evaluated in small residential environments unlike the large public buildings of real deployment. We introduce SlugTrails, a floor plan localization benchmark for large indoor spaces under realistic egocentric sensing:

30

Hz Aria glasses recordings across three campus buildings and six floors (

22089

^2

of floor plan outline), CAD-derived floor plans with semantic classes and circulation space masks, and trajectories aligned into the floor plan frame using laser-surveyed anchors. One protocol covers three practical ways of gathering geometry under a limited field of view -- a single walking frame, a stationary multi-view sweep, and a walking stream with odometry -- so methods designed for different regimes are compared on the same buildings and ground truth. Evaluating five representative geometric and learned systems under their native sensing configurations, we find that stock checkpoints (official released weights) are near zero on SlugTrails (at most

0.004

R@1m30

^{\circ}

on walking single frames), while fine-tuning on SlugTrails improves every trainable family on all three tasks (e.g., F

^3

Loc

0.0 \rightarrow 0.141

single-frame and

0.03 \rightarrow 0.66

sequential), with gains compounding as observations accumulate. The same fine-tuned weights also improve cross-dataset generalization on LaMAR with no LaMAR training (sequential R@1m

0.048 \rightarrow 0.143

for F

^3

Loc and

0.063 \rightarrow 0.127

for UnLoc), whereas train-from-scratch on SlugTrails alone stays far below fine-tuning from stock weights -- evidence that floor plan localization is currently limited by indoor data rather than by architecture. We release the dataset, protocols, and tools at https://github.com/Head-inthe-Cloud/SlugTrails.

Abstract

Trajectory Inference

Explore similar work

SlugTrails: An Egocentric Benchmark for Floor Plan Localization in Large Buildings

LangLoc: "Tell Me What You See"

Evaluating Memory Capability in Continuous Lifelog Scenario