Build a Gesture Recognition Wand with ESP32 & Edge Impulse – Classify Walking, Running & Idle

Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.

Move the wand and watch it instantly recognise whether you're walking, running, or idle — all processed on a compact ESP32-S3 using a TensorFlow Lite model trained in Edge Impulse. This kit is the perfect launchpad for sports analytics prototypes, AR input devices, or fitness tracking mini-projects.

What You'll Build

You'll assemble a handheld gesture-recognition device that reads 6-axis motion data from the MPU6050, runs an on-device TinyML classifier, and displays the predicted activity on a bright 0.96‑inch OLED screen. The wand can distinguish between three distinct movement states in real-time, giving you a tangible, wearable-ready prototype to demonstrate or extend.

What You'll Learn

• Collecting and labelling IMU sensor data for machine learning
• Building a motion classification model in Edge Impulse
• Deploying a TensorFlow Lite model on ESP32-S3
• Using I2C protocols to interface MPU6050 and OLED display with the microcontroller

Kit Contents

Why Buy This Kit Instead of Sourcing Parts Separately

Who This Kit Is For

This kit is ideal for CBSE Class 11–12 students exploring AI/ML practicum, B.Tech ECE/EEE undergraduates building a mini project, Smart India Hackathon participants prototyping a wearable activity tracker, and ATL Tinkering Lab coordinators seeking a ready-to-assemble embedded ML module. If you're comfortable with Arduino IDE and want to go beyond blinking LEDs, you're ready for this.

Built and Backed by Compoden

Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We've spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.