Smart bin that sorts recycling automatically at the point of disposal
Software: $79–$199 per month
Pilot deployments begin ahead of general availability (Q4 2027). The optional $49 pilot-slot deposit is fully refundable.
Real-time 3D render · drag to rotate · final design may vary
What it is
A smart recycling bin with a camera that opens the right lid for you.
What it does
Who it's for
Offices, campuses, airports, malls, stadiums and hospitals.
Look inside
Keep scrolling: it opens up in real time to show the parts that do the work.
Overview
WasteSort AI is a 3- or 4-compartment smart bin with a camera, edge AI processor and servo-driven lids. It recognises each item as it is presented, classifies the material — plastic, paper, metal, general waste — and opens the correct compartment, while tracking waste types and volumes for sustainability reporting.
The problem
People sort waste wrongly most of the time, contaminating recycling streams and sending recyclable material to landfill. Offices, schools, airports, malls and stadiums face rising waste costs and sustainability-reporting obligations, but have no data on what is thrown away or how well it is sorted.
Open the right lid for each item so recycling streams stay clean.
Increase recycling diversion rates in offices, campuses and public spaces.
Handle heavy use at airports, malls and stadiums with fast item recognition.
Teach sorting with on-screen feedback that shows what each item is and where it goes.
Track waste type and quantity for ESG and local reporting requirements.
Use fill-level data to schedule pickups only when bins are full.
A person holds an item under the camera at the top of the bin.
The on-device model identifies the item and material type in under a second.
Servo motors open the correct compartment lid; the screen confirms the choice.
Weight sensors and fill-level tracking record each deposit.
The dashboard shows volumes, recycling rate, contamination and pickup needs per bin.
In the app
The WasteSort dashboard shows every bin's fill level, recycling rate and contamination, with exportable sustainability reports.
Plastic compartment at 88%
Lined coffee cup → general waste
Paper lid motor stalled, retrying
Recycling up 6 pts vs last week
Runs on-device · Hailo-8L
Identifies common waste items such as bottles, cans, cups, cartons and wrappers.
Model: MobileNetV3 / YOLO11-n
Classifies material — plastic, paper, metal, glass, organic, general.
Model: Fine-tuned EfficientNet-Lite classifier
Separates the item from hands and background for accurate classification.
Model: SAM2-distilled segmentation (EfficientSAM)
Models are trained and continually improved on real-world waste images from pilot sites.
Model: Active-learning pipeline
Predicts when each compartment will be full.
Model: Gradient-boosted time-series model (cloud)
Targets for production units. Subject to change during development.
| AI processor | Hailo-8L (13 TOPS) or NVIDIA Jetson Orin Nano |
|---|---|
| Camera | 1080p wide-FOV camera with LED illumination |
| Sensors | Weight sensor per compartment (optional) · Ultrasonic fill-level sensors · Proximity sensor |
| Connectivity | Wi-Fi · 4G LTE · Ethernet (optional) |
| Power | 24 V / 12 V mains supply, 15–30 W |
| Enclosure | Powder-coated steel body with colour-coded lids and touch-free servo actuators |
| Dimensions | 60 × 35 × 45 cm (3-bin module) |
| Weight | ~22 kg |
| Ingress rating | IP44 (indoor / covered outdoor) |
| Camera | 1080p, wide FOV |
|---|---|
| Processor | Hailo-8L (13 TOPS) / Orin Nano |
| Classification time | < 1 s per item (target) |
| Classes at launch | Plastic, paper, metal, general (+ glass / organic configurable) |
| Actuators | Servo motors and lid control |
|---|---|
| Configurations | 3-bin or 4-bin system |
| Capacity | Approx. 40 L per compartment (target) |
| Display | 7-inch screen for feedback |
| Weight sensing | Optional, per compartment |
|---|---|
| Fill level | Ultrasonic |
| Network | Wi-Fi / 4G |
| APIs | REST, webhooks |
| Power | 15–30 W, 24 V / 12 V |
|---|---|
| Size | 60 × 35 × 45 cm |
| Weight | ~22 kg |
| Rating | IP44 |
Built with
Proven, off-the-shelf components our prototypes are built on. Final production parts may differ.
Raspberry Pi 5
Main computer for our edge boxes
Photo: SimonWaldherr,CC BY 4.0, via Wikimedia Commons · AI overlay added
Raspberry Pi AI HAT+ (Hailo AI accelerator)
Runs the vision models on the device
Photo: SparkFun Electronics,CC BY 2.0, via Wikimedia Commons · AI overlay added
NVIDIA Jetson Orin module
Higher-power option for large sites and robots
Photo: 4300streetcar,CC BY 4.0, via Wikimedia Commons · AI overlay added
Micro servo motor
Moves heads, tails and lids
Photo: Suyash Dwivedi,CC BY-SA 4.0, via Wikimedia Commons · AI overlay added
Load cell (weight sensor)
Weighs each compartment
Photo: Gannu03,CC BY-SA 4.0, via Wikimedia Commons · AI overlay added
Reference photos of commercially available components. IEMI Labs is not affiliated with or endorsed by their manufacturers. Photo credits
Planned contents
The WasteSort dashboard shows every bin's fill level, recycling rate and contamination, with exportable sustainability reports.
Hardware: $399–$2,199 per unit
Software: $79–$199 per month
Start with Bin Insights on your existing bins, or choose a full sorting bin. Weight sensing is included on Sort 4.
$399 + $79/mo
Contamination analytics on your existing bins.
$1,499 + $99/mo
3-bin sorting model for offices and schools.
$2,199 + $199/mo
4-bin model with weight sensing.
Indicative launch pricing in USD, excluding taxes and shipping. Final pricing is confirmed before any balance is charged.
Illustrative estimates based on internal modelling and typical deployments; not measured results. Actual outcomes depend on site conditions and usage.
Target milestones. We will email reservation holders and pilot partners as they change.
Q4 2026
Pilot applications open; classification prototype collecting real-world waste images
Q1 2027
Servo lid mechanism and 3-bin chassis prototype
Q2 2027
EVT builds; durability testing for high-traffic use
Q3 2027
Pilot deployments at offices, campuses and public venues
Q4 2027
First production shipments
2027 Pilot Program
Pilot partners get early hardware, direct engineering support and preferential launch pricing. Tell us about your site and cameras.
How the pilot program worksA member of the IEMI Labs team will reply within two business days.
No. Applying is free and carries no obligation. If you want to hold a pilot slot, you can place an optional $49 deposit. It is fully refundable any time before shipment — email [email protected] or use the refund link in your confirmation email — and it is credited in full against your purchase if you go ahead.
Yes. Item recognition runs on the bin. The camera looks down at the item area, images are processed on-device and discarded, and only counts and material types are sent to the dashboard.
Unrecognised items default to general waste, and the screen asks the user to confirm. These cases help improve the model over time.
Place the bin, connect power and Wi-Fi or 4G, and register it in the dashboard. Liners are standard sizes.
Over Wi-Fi or the built-in 4G modem. Sorting works offline; data syncs when connectivity returns.
WasteSort AI is in development. Specifications shown are target specifications and may change as we complete engineering validation. We are targeting a Q4 2027 ship window and will email reservation holders with every major milestone.
We are planning a 2-year limited hardware warranty covering manufacturing defects, with advance replacement for pilot and business customers. Final warranty terms will be published before shipping begins.
A palm-sized edge box that plugs into your existing parking cameras.
From $499 per edge box (waived on a 12-month plan)
PilotA small ceiling-mounted camera that watches shop and warehouse floors.
From $399 per edge box
PilotA lunchbox-sized monitor that mounts inside trucks, cold rooms and fridges.
From $199 per kit (free on 12-month restaurant plans)
ReserveWasteSort AI
From $399 · Ships Q4 2027