Project Hub /Artificial Intelligence & Edge ML/Face Recognition & Access Control/Bao, AI Pet Dog

Intermediate

ESP32

Project Specific

6 – 12 Hours

Partial Kit

Bao, AI Pet Dog

An AI-powered robotic pet dog that responds to offline voice commands, performs face recognition, and features a mobile app Bluetooth control interface.

Originally published on CircuitDigest

View original tutorial

How It Works

Bao, the AI Pet Dog, integrates multiple hardware modules to achieve advanced robotics and edge artificial intelligence capabilities. At its core, the system relies on an ESP32 WROVER Dev Module and a Sipeed Maixduino board. The Maixduino handles intensive edge AI tasks, specifically running computer vision algorithms like face recognition captured via compatible AI vision hardware, alongside a pan-tilt head driven by two SG90 9gm servos. For mobility, four N20 geared motors paired with N20 wheels are commanded through an L298N H-Bridge motor driver, which translates low-level control signals from the microcontroller into high-current power for driving the chassis. Voice interaction is managed through the Ai-Thinker VC-02 module, enabling offline voice command processing. Power is supplied by two 18650 Li-PO batteries held in a dedicated battery holder, regulated through a Lipo toggle switch, and distributed across the perf boards using custom wiring, male-female headers, and heat shrink tubes. Software execution spans MicroPython, the MaixPy IDE, the SIPEED OEM flasher, and the Arduino IDE, allowing developers to program both the vision models and general-purpose input/output interactions.

Why Build This

Gain hands-on experience combining computer vision and edge AI with physical robotics chassis construction.

Learn to integrate diverse microcontrollers, motor drivers, and voice recognition modules into a cohesive autonomous pet system.

Develop practical programming skills using MicroPython and Arduino IDE for hardware control and machine learning deployment.

Real-World Application

STEM education, robotic companionship, edge AI prototyping, and interactive home assistant development.

Skills You'll Learn

Edge AI deployment

computer vision face recognition

DC motor speed and direction control via H-bridge

servo motor positioning

offline voice recognition integration

power management with lithium-ion batteries

microcontroller programming

Safety Precautions

Handle lithium-ion batteries with care, ensure correct polarity to prevent short-circuiting, and use appropriate thermal shrink tubing and wire management.

Technology Tags

ROBOTICS

FACE RECOGNITION

VOICE CONTROLLED

VOICE ASSISTANT

BLUETOOTH

IOT AND EDGE AI

3D PRINTING

ESP32

ARTIFICIAL INTELLIGENCE

MICROPROCESSOR

ARDUINO IDE

MICROPYTHON

MOTORS

LITHIUM BATTERIES 18650 NMC

Frequently Asked Questions

Can Bao recognize faces without an active internet connection?

Yes, face recognition is processed locally on the edge using the Sipeed Maixduino hardware, meaning it does not require cloud connectivity or an active internet connection.

How do I program both the ESP32 and the Sipeed Maixduino?

You can use a combination of the Arduino IDE, MaixPy IDE, and MicroPython, uploading code separately to each board using Type-C and micro USB cables depending on the specific module's architecture.

What is the purpose of the L298N H-Bridge in this robot?

The microcontrollers cannot supply enough current to drive the four N20 DC motors directly. The L298N H-Bridge acts as an intermediary power amplifier, allowing the control board to safely command the movement and direction of the wheels.

Gallery

This page is part of Kitkraft's Project Hub — a curated collection of electronics & robotics projects gathered from the maker community to help students and hobbyists discover and learn to build. Kitkraft does not claim authorship of the original project, and makes no representation as to the accuracy, completeness or safety of third-party source material. The summary and "How It Works" explanation above are AI-generated, rewritten with reference to the original tutorial — not a reproduction of it. Full credit and a direct link to the original source are provided above. If you're the original creator and have a concern about how your work is represented here, please contact us and we'll address it promptly.

Kitkraft Project Hub — curated from the maker community, credited at the source.

PRJ-01076