An IoT Based Approach for Platform Independent Positioning Service

summary

The gist

KAIST Indoor Localization System (KAILOS) was introduced in 2014 and became one of the world-first complete indoor positioning solutions.

In short

This study extends the KAIST indoor localization system by introducing an IoT-based approach to overcome mobile app limitations imposed by operating systems like Android and iOS. A dedicated wearable device collects sensor data, allowing users to access precise indoor positioning services independently of smartphone restrictions. This offers a platform-independent solution with improved accuracy and flexibility.

Key concepts

Extended KAILOS Architecture
This is an enhanced system design that integrates a dedicated IoT device with mobile applications and servers. The goal is to bypass operating system limitations on signal scanning, enabling the positioning service to work reliably across different phones without needing app installations or OS-specific permissions.
IoT Device Functionality
A specially designed wearable hardware unit equipped with multiple sensors including WiFi, 4G LTE, IMU (Inertial Measurement Unit), and GNSS. It operates in three phases: initializing, positioning (scanning WiFi signals via LTE), and sleeping. This device acts as the primary data collector for location estimation.
Sensor Fusion and Dead Reckoning
This involves combining data from different sensors like IMU (accelerometer/gyroscope) and WiFi signal measurements to estimate a user's position. Pedestrian dead reckoning uses this fused data at high sampling rates (e.g., 100Hz) to create a more accurate trajectory compared to lower rates.
Platform Independence
The system is designed so that the positioning service works regardless of the underlying mobile operating system (Android or iOS). By offloading signal scanning and data processing to a dedicated hardware device, users gain access to location services without being constrained by OS restrictions.

Terminology used across episodes

This episode discusses

The paper

An IoT Based Approach for Platform Independent Positioning Service · Read on arXiv

Anh-Van Vu, Dongsoo Han

Korea Advanced Institute of Science and Technology

Transcript

Introduction to the show: ident: Robotics Radio. Generated commentary on the latest robotics and control papers.

Rosa: We're looking at the paper: "An IoT Based Approach for Platform Independent Positioning Service".

Title and authors: Rosa: So we’re talking about this paper called "An IoT Based Approach for Platform Independent Positioning Service". Rosa, what’s the big picture here?

Dev: It’s about taking a system that used to be stuck inside a mobile app on an Android or iOS phone and making it work everywhere by using an Internet of Things device.

Rosa: Exactly. The core idea is moving the heavy lifting of signal collection off the phone itself and onto this dedicated hardware, which then feeds into the location service through a server.

Dev: It’s trying to remove those OS restrictions that limit how fast or how often you can scan for WiFi signals, which was a big problem with earlier systems like KAILOS.

Taro: So it sounds like they are trying to build something that doesn't care if the user is on an iPhone or an Android, which is a practical goal in real-world deployment.

Rosa: Right. The authors introduce this extended architecture, which includes a dedicated IoT device paired with the smartphone for accessing positioning services, even when the phone’s operating system restricts access to WiFi signals at a high rate.

Dev: It sets up this whole framework involving the IoT device, front-end server, back-end server, database, and map registration tools to manage everything.

The paper's summary: Rosa: So what’s the actual mechanism they propose? Basically, they suggest that instead of relying on the phone to constantly scan for WiFi signals at a high frequency, this hardware device does that work independently.

Dev: The IoT device has a processing unit with WiFi, 4G LTE, Bluetooth low energy, an IMU sensor for movement data, and even GPS. It’s designed to handle the signal collection in different phases: initializing phase, positioning phase, and sleeping phase.

Rosa: During the positioning phase specifically, this device scans available WiFi signals and sends that collected data to the server via 4G LTE so it can estimate its location.

Dev: And that data goes into a database that stores indoor maps, radio maps, and sensor data collected from these end devices, which is key for building a comprehensive positioning picture.

Taro: That database structure sounds important because it’s not just about one device; it’s about crowdsourcing information to build a richer map for everyone.

Rosa: They also focus on how this architecture helps users access locating services regardless of the operating system, solving that platform dependence issue they mentioned earlier.

Dev: It basically says that by using this IoT approach, you get the advantage of non-OS constraints and potentially group user benefits because many people can contribute to the map data.

The paper's improvements: Rosa: One major improvement they highlight is moving away from the mobile app being the sole source of signal input, which was a huge limitation because Android and iOS have very different rules on how much WiFi scanning you can do.

Dev: They show that this IoT-based approach offers advantages in terms of accuracy, scanning frequency, and time per scan when compared to just using the standard Android or iOS apps alone.

Taro: I saw something about pedestrian dead reckoning experiments too; they tested different sampling rates on the movement data from the IoT device.

Rosa: Yes, they did. They found that for pedestrian dead reckoning experiments, using a higher sampling rate, like one hundred Hertz data, gave a better match with the ground truth trajectory compared to lower rates like twenty-five Hertz or fifty Hertz data.

Dev: That’s because you can adjust the sampling frequency independently on the hardware device, which lets you optimize how much data you collect for your specific needs.

Taro: And they also added some clever pre-processing to their WiFi fingerprinting results; they mentioned that the device detects and removes abnormal access points by checking missing information from each AP before selecting only the top twenty ranked APs.

Rosa: So, it’s not just about collecting more data; it’s about cleaning up the data you collect so that the final location estimation is more robust against bad signals.

Conclusion: Dev: To wrap this up, the paper suggests that having a dedicated positioning hardware device equipped with various sensors provides high-quality data for the location server by removing those OS restrictions entirely.

Rosa: It shows that this approach is promising because it allows users to access locating services regardless of their mobile platform and gives them control over signal collection periods for each sensor.

Taro: What this means for the future is that we’re looking at the very first step toward producing an indoor outdoor positioning system on a wearable device, which opens up new possibilities beyond just smartphone applications.

Dev: It's about creating a system where the hardware handles the heavy lifting, freeing up mobile platforms to focus on other things, and that’s how you get better performance.

Rosa: So it really comes down to using this IoT based approach for platform independent positioning service to unlock real-life applications for indoor localization services across different devices.

More episodes

← Home