Mobicom 2022 | Practical Indoor Localization for Malls

Abstract

We report our experiences of developing, deploying, and evaluating MLoc, a smartphone-based indoor localization system for malls. MLoc uses Bluetooth Low Energy RSSI and geomagnetic field strength as fingerprints. We develop efficient approaches for large-scale, outsourced training data collection. We also design robust online algorithms for localizing and tracking users’ positions in complex malls. Since 2018, MLoc has been deployed in 7 cities in China, and used by more than 1 million customers. We conduct extensive evaluations at 35 malls in 7 cities, covering 152K m^2 mall areas with a total walking distance of 215 km (1,100 km training data). MLoc yields a median location tracking error of 2.4m. We further characterize the behaviors of MLoc’s customers (472K users visiting 12 malls), and demonstrate that MLoc is a promising marketing platform through a promotion event.

System Design

MLoc consists of two phases: offline training, where (fingerprint, location) pairs are collected to build a localization model, and online inference, where a user’ smartphone collects fingerprints, uploads them to the edge, and obtains the location and/or navigation guidance in real time.

Beacon deployment

We walk between landmarks to collect the fingerprints of the building

Fingerprint collecting

Corner cases of localization (narrow corridor, and dead end)

Paper | Talk | Slides

Cite Us

            @inproceedings{hu2022mloc,
              author = {Yuming Hu, Feng Qian, Zhimeng Yin, Zhenhua Li, Zhe Ji, Yeqiang Han, Qiang Xu, Wei Jiang},
              title = {Experience: Practical Indoor Localization for Malls},
              year = {2022},
              isbn = {781450391818},
              publisher = {Association for Computing Machinery},
              address = {New York, NY, USA},
              url = {https://doi.org/10.1145/3495243.3517021},
              doi = {10.1145/3495243.3517021},
              booktitle = {The 28th Annual International Conference On Mobile Computing And Networking (ACM MobiCom '22)},
              pages = {82–93},
              numpages = {12},
              location = {Sydney, NSW, Australia},
              series = {Mobicom '22}
            }

MLoc Dataset

MLoc has been deployed since 9/2018 with improvements being made over the past three years. We have conducted principled, large-scale evaluations by hiring trained testers. We release the data used in the paper, most of which is collected in the past two years. MLoc adopts an outsourcing approach (i.e., hiring paid human workers) for collecting BLE/GMF fingerprints and the ground truth location data. The details of the data format can be found here, and an example of the trace file is shown here.

Localization errors under different algorithms.

Localization errors under different time.

Localization errors under different BLE broadcast interval.

Download (MLoc) Sample

All 40GB dataset (8GB compressed).

Supporters

This project was supported in part by NSF Award 1915122 and 2128489. Zhimeng Yin’s research was supported by City University of Hong Kong 9610491 and NSF China 62102332.