R&D / AI drone concept and proof of concept

Drone Proof Of Concept Development: A Follow-Me Drone With Wearable Alerts

Proof of concept for a companion drone that follows its user and sends alerts to a phone and wristbands.

Concept rendering of a shark-styled quadcopter with a camera, a smartwatch screen showing a red marker 50 m from the wearer, and silhouettes of a shark and a diver 50 m apart.

The opportunity

A vision without an architecture

Hover Hero had a concept for a compact companion drone for open-water users. The founders had no architecture, selected hardware or software yet.

The solution

Show that it is feasible

Indeema documented the architecture, tested follow-me on a real platform, trained a detection model and defined the alert flow to phone and wristbands.

  1. 01Architecture
  2. 02Drone platform
  3. 03Follow-me mode
  4. 04Detection model
  5. 05Alert flow
Hover Hero drone hardware diagram: flight controller linked to an ESC, RTK GPS, LiDAR rangefinder and an edge-processing module with a wide camera; a phone gets RTSP video and BLE telemetry and pairs with a watch.

The impact

What the founders received

  • High-level ideaDocumented system architecture
  • Platform not chosenPlatform chosen through tests with the client
  • No detection modelNeural network trained and evaluated on images
  • No planEngineering documents and development plan

A proof of concept: alerts were tested with simulated targets on a floor, not with real sharks in open water.

Engineering judgement

Decisions that shaped the product

Reuse an existing hardware platform

Build on Indeema's existing drone hardware to speed up early validation.

Defer custom firmware

Use Betaflight or iNAV for flight control in the proof of concept, leaving room for custom firmware later.

Simulate the threat

Use a projector showing moving shapes as targets, so detection and alerts could be tested in a controlled setting before any open-water work.

Train the model in our own lab

Annotate drone-view imagery and train and evaluate the shark-detection network in Indeema's lab, measuring precision and recall at several input sizes.

Keep detection on the drone and lightweight

Choose a compact neural network, YOLO11n, suited to on-board processing so the alert path stays responsive.

Decide distance with field tests

Settle the follow-me configuration through real-world tests with the client rather than on paper.

Built with

Swift · C/C++ · Python · Betaflight / iNAV · STM32F405 · Silicon Labs EFM8BB21 · ESP32-C6 · YOLO11n

More case studies

All case studies ↗

A comparable product problem?

Hover Hero: companion-drone proof of concept

Discuss a comparable challenge