EchoScan

The description states that EchoScan is an Android app that emits high-frequency audio chirps (30 ms, 14–18 kHz Hann-windowed) and uses echo correlation to detect objects within 50 cm. It processes the audio locally using cross-correlation between the emitted signal and the returning echo to determine object presence, approximate distance, and confidence level.

It is described as a biomimetic sonar system inspired by bat echolocation, built natively for Android with Kotlin and Jetpack Compose.

Evidence The author’s own write-up describes how it works technically, including use of AudioTrack/AudioRecord for full-duplex audio, cross-correlation algorithm, and distance calculation using speed of sound.

Inference This is a software-based sonar system that relies on smartphone hardware to simulate echolocation. It does not appear to be a commercial product or service yet.

The author claims the app turns a standard Android phone into a short-range acoustic detector, leveraging AI and advanced signal processing to achieve spatial sensing without specialized hardware.

It positions itself as an experiment in biomimetic sonar using everyday mobile devices, inspired by WiFi-based wall-seeing experiments and AI-assisted development.

Evidence The write-up states the inspiration came from watching a video about seeing through walls with WiFi waves, leading to the idea of building something similar using smartphone sensors.

Inference The positioning is experimental and exploratory. It does not claim commercial viability or widespread adoption.

Not evidenced.

The description does not identify any specific customer segment or target market beyond a general interest in accessibility or spatial sensing technology.

Evidence No mention of end users, personas, or use cases beyond the MVP demonstration.

Not evidenced.

There is no indication of pricing, monetization strategy, or business model. The project is described as a hackathon submission with no commercial intent or revenue streams mentioned.

Evidence The write-up focuses on technical implementation and AI collaboration; no mention of sales, subscriptions, licensing, or any form of monetization.

The app was built natively for Android using Kotlin, Jetpack Compose, and a clean architecture with domain/data/ui separation. It uses AudioTrack and AudioRecord to bypass standard audio processing and implements full-duplex audio pipelines.

It includes deterministic chirp generation, PCM manipulation utilities, cross-correlation logic, and UI states designed around the acoustic engine’s output.

The AI (GPT-5.6 and Codex) was used for scaffolding, code writing, algorithm design, and testing, acting as a pair programmer throughout development.

Evidence The author describes the technical stack and workflow in detail, including challenges like direct coupling and near-field dead zones.

Inference The app is technically sophisticated for a hackathon project but remains an MVP with no production deployment or scalability claims.

Not evidenced.

There is no evidence of user adoption, customer feedback, usage metrics, or product maturity beyond the initial build week. No data on downloads, retention, or real-world performance is provided.

Evidence The project was submitted to a hackathon and described as an MVP with no follow-up or commercial rollout.

Not evidenced.

No information is given about existing competitors or similar technologies in the market. The description does not reference other sonar systems, accessibility tools, or spatial sensing solutions.

Evidence No mention of prior art or competitive landscape.

• Prototype-only: The project is described as a hackathon MVP with no evidence of further development or commercialization.
• No traction or customers: There is no indication that the app has been used by anyone beyond its creator.
• AI dependency: Heavy reliance on AI tools (GPT-5.6, Codex) raises questions about whether this could be replicated without such tools or if it’s a one-off experiment.
• Hardware limitations: The system depends heavily on Android device audio capabilities, which vary widely across models and may not support consistent performance.

Evidence The author explicitly states the project is an MVP built in a short time and submitted to a hackathon.

1. Has the app been tested on multiple devices beyond the OnePlus 3T used for calibration?
2. Are there any plans or early signs of commercialization or product development beyond this MVP?
3. What is the current status of the AI collaboration — is it still actively involved in development, or was it only used during the hackathon?
4. Have you considered how to scale this across different Android hardware profiles and latencies?
5. Is there any feedback from users or accessibility communities who might benefit from such a tool?