The Edge AI Air Detective

Your city app says AQI 142. Your gali says "run."

Evaluation only · Open

Build an air quality node that thinks for itself. No cloud, no subscription, no waiting for a server in some data centre to tell a child in Cuttack whether the playground is safe today. All AI inference runs on the Arduino UNO Q sitting right there in the smoke.

Overview

Outcomes - Hyperlocal air quality intelligence that works offline and costs nothing per node to run - Actionable guidance for daily life instead of a raw number nobody can interpret - Source attribution that helps an RWA, school or municipal body fix the cause, not just record the effect - Privacy-preserving operation — raw audio, images and location never leave the device - A low-cost reference design schools and local bodies can actually replicate Overview Air quality monitoring today is a group project where one member does all the work, and that member is the cloud. Sensor nodes push raw readings up, every decision waits on connectivity, bandwidth and a paid plan, and the citizen gets one number for an entire city. That number says nothing about the road you walk on, the classroom you sit in, or the kitchen you cook in. The gap is not sensing. The gap is interpretation, at the place where the pollution is actually happening. Edge AI closes it. The Story It is 7:40 AM. The app says the city is "Moderate." Your neighbour is burning last night's plastic in a drum. Your mother has already opened every window for "fresh air." The nearest official monitoring station is eleven kilometres away, next to a park, having a lovely time. Everyone in this scene is making decisions using a number that was true somewhere else, for someone else. Fix that.

The brief

Senses PM2.5, PM10, CO, CO₂, NO₂, VOCs, temperature and humidity, and runs all inference locally with no cloud round trip
Forecasts the next few hours of hyperlocal air quality from the node's own sensor history using a small on-device time series model
Identifies the likely pollution source from sensor signatures — traffic, garbage burning, construction dust, cooking smoke, crop residue — using sensor fusion, optionally with camera or microphone input
Converts readings into an action the user can take that day: change a walking route, time the opening of windows, run an exhaust fan, move an outdoor activity indoors
Keeps working through power cuts and network outages, storing data locally and syncing only compressed summaries when a link appears
Scales to multiple nodes across a campus, colony or ward so a street-level pollution map can be built with zero per-node cloud cost

Mandatory hardware requirement: The solution must be built on the Arduino UNO Q. All AI inference must run on the board itself. Cloud APIs and external AI services may not be used for core decision-making. Sensors, actuators, displays and communication modules are your choice, but the UNO Q must be the computing platform of the submitted prototype.

Technical feasibility (the cheat sheet): Board — UNO Q pairs a Qualcomm Dragonwing QRB2210 quad-core Cortex-A53 running Debian Linux with an STM32U585 MCU for real-time sensing, giving both AI capability and deterministic sensor timing on one board. Sensors — PMS5003 or SPS30 for particulates, MQ135 and MiCS-6814 for gases, SCD41 for CO₂, BME688 or DHT22 for temperature, humidity and VOC index, Modulino nodes over I2C for fast prototyping. Software — Arduino App Lab with its Python and C++ bricks; the Linux side runs the model, the MCU side handles acquisition and actuation. Models — quantised TensorFlow Lite or ONNX Runtime, gradient boosting for classification, a compact LSTM or TCN for forecasting, optionally a small language model fully on-device for the advisory layer. Connectivity — on-board Wi-Fi and Bluetooth, LoRa or GSM as an add-on for outdoor nodes. Power — USB-C, or a solar panel with a LiFePO4 pack for a fully off-grid node.

Deliverables

A working UNO Q node that senses the required parameters and runs classification, forecasting and advisory entirely on-device
The on-device forecasting model plus source-attribution logic, with training approach and quantisation documented
A proof-of-offline run: pull the network, pull the mains, show it still sensing, deciding and advising
A user-facing output layer that gives a plain-language action, not just a number
A multi-node scaling plan with at least a two-node street-level view demonstrated, plus a bill of materials and per-node cost

Evaluation criteria

On-device intelligence and offline integrity (no cloud in the decision loop) — 30%
Sensing accuracy and quality of hyperlocal forecasting — 25%
Source attribution and real-world actionability of advice — 20%
Hardware craft, power efficiency and multi-node scalability — 15%
Demo quality and clarity of storytelling — 10%

More challenges to enter

Prizes are offered and awarded by Arduino S.R.L., not by Wooble. Amounts shown are as stated by the host and may include the host’s own valuation of non-cash items. Who places, how and when a prize is paid, and any tax or deduction, are between the winner and the host. A challenge may close, change or be withdrawn before results are declared.