Inspiration
What it does
How we built it
Challenges we ran into
Accomplishments that we're proud of
What we learned
What's next for smart campanion
🚗 What it does
Moves in all directions using 4 BO motors (including smooth 360° spins).
Expresses emotions through LCD baby-like animated eyes.
Uses a camera for face recognition and interaction.
Speaks and converses with users, powered by LLaMA + ChatGPT AI.
Learns over time — remembers voices, adapts responses, and grows with the user.
Controlled by an ESP32 brain mounted on the bonnet.
🛠️ How we built it
Hardware: ESP32 (main brain), 4 BO motors with motor driver, LCD display, camera module.
Software:
Arduino C++ for ESP32 motor control & sensor handling.
Python backend for AI logic, voice recognition, and memory.
LLaMA + ChatGPT APIs for natural conversation.
Integrated real-time emotion animations (happy, curious, excited) on the LCD.
Designed the car body as a miniature BMW M4, combining futuristic and playful aesthetics.
⚡ Challenges we ran into
Syncing real-time motor actions with emotional expressions.
Managing limited ESP32 processing power for both control and interaction.
Training the “baby-like” learning system to remember users without losing responsiveness.
Designing smooth and natural eye animations on the LCD.
🏆 Accomplishments that we're proud of
Successfully made the car feel alive, not just robotic.
Built a 360° maneuver system that works seamlessly.
Integrated AI conversation (LLaMA + ChatGPT) into a moving physical companion.
Created an emotional UI (eyes + sounds) that makes it feel like a real baby robot.
📚 What we learned
How to merge robotics + AI + design into one product.
Optimizing ESP32 for multi-tasking (motors, sensors, communication).
Balancing technical complexity with emotional engagement.
The importance of creating intuitive personality traits in robots.
🚀 What’s next for Smart Companion
Adding gesture recognition with the camera.
Enabling voice cloning to make it sound more natural.
Cloud-based memory so it can learn across devices.
Scaling up from a toy model to a full-sized companion car prototype.
Exploring smartphone app integration for remote control + training.
we dint have money to do this
Log in or sign up for Devpost to join the conversation.