Back to Case Studies
IoT & Industrial
VendAI
AI Smart Vending Machine based on ESP32-C6
AI-powered vending machine that recognizes each product via camera, eliminating the need for spiral dispensers or complex mechanical sensors.
Product Recognition
98%
Payment Methods
8
VendAI
Client
A vending machine operator seeking to retrofit existing machines with a universal AI perception system that recognizes products visually.
Challenge
Recognizing 200+ SKUs with varying packaging (cans, bottles, bags, boxes) in a refrigerated, glass-front environment with reflections and variable lighting.
Product Concept & Architecture
The ESP32-C6 Wi-Fi 6/BLE SoC is paired with an OV5640 camera mounted behind the glass. A 7-inch TFT touch display handles user interaction.
Engineering Solution
When a product is removed, the camera captures an image. An INT8-quantized EfficientNet-Lite model (800KB) on the ESP32-C6 classifies the product from 200 SKUs in under 200ms. An anomaly detection model flags unrecognized products for operator review.
Result
98% product recognition accuracy across 200 SKUs. <200ms per transaction. 30% increase in sales.
Deep Tech FAQ
What makes the AI Smart Vending Machine based on ESP32-C6 unique?+
The AI Smart Vending Machine based on ESP32-C6 leverages custom hardware and edge AI to deliver industry-leading performance and efficiency.
What are the core technical benefits?+
Key benefits include low power consumption, real-time processing, robust connectivity, and a compact form factor tailored for deployment.
Can this architecture be adapted for other use cases?+
Absolutely. The underlying methodology is modular and can be retargeted for various applications with minimal redesign.
Project Profile
Services Delivered
Hardware DesignEmbedded Software
Core Technologies
Wi-Fi/BluetoothComputer VisionRTOS
Silicon & Vendors
EspressifOmniVision
Need similar outcomes?
Let's discuss how ChipTalk can deliver results for your next project.
Tell us about your project.
Fast Response — Initial feedback within 48 hours
Full R&D Lifecycle — From feasibility to mass production
Extensive Experience — 500+ projects across 15 verticals
Rapid MVP Validation — Prototype in as fast as 12 weeks
Portfolio
