We will be undergoing planned maintenance on January 16th, 2026 at 1:00pm UTC. Please make sure to save your work.

Inspiration

The idea for Void was born out of a simple observation: air is fluid, but air purifiers are static. Traditional purifiers sit in a corner, cleaning only a small radius while pollutants and allergens remain trapped in "dead zones" across the room. Seeing the efficiency of robotic vacuum cleaners, I realized that clean air shouldn't be a luxury of location. I wanted to build a proactive guardian that doesn't just wait for pollution but actively hunts it down to ensure every corner of a home is safe.

What it does

Void is an autonomous, IoT-integrated air sentinel. It utilizes SLAM-based navigation to map a house and patrol rooms based on real-time Air Quality Index (AQI) levels. Beyond purification, it acts as a home security hub:

Emergency Response: If the MQ-series sensors detect smoke, Void triggers an Alexa alert and notifies the owner/emergency services.

Remote Control: A dedicated mobile app allows users to "pre-clean" their home from the office and also helps monitor infants and pets remotely.

Smart Analysis: It uses AI to monitor usage history and predict filter replacement needs.

How we built it

Since we are in the initial R&D phase, we focused on building a robust Technical Blueprint and Digital Prototype.

System Architecture: We architected a multi-layered IoT stack. The "brain" is designed to handle real-time sensor fusion from PM2.5, MQ-135, and DHT11 sensors.

Navigation Logic: We developed the logic for a "Path-Planning Algorithm." Instead of random movement, the robot is designed to calculate a cleaning path based on the house blueprint using a grid-based mapping system.

Visual Prototyping: We used Figma to design the user interface for the mobile app and utilized CAD modeling to determine the physical placement of filters and fans for maximum airflow efficiency.

Challenges we ran into

The primary challenge we currently face is Capital & Prototyping Costs. High-quality hardware—specifically Lidar sensors for navigation, high-static pressure fans, and HEPA-grade filters—requires significant upfront investment.

Financial Barrier: As first-year students, we lack the initial funding required to move from a digital schema to a high-fidelity physical prototype.

Hardware Selection: We are currently in a "Trade-off Analysis" phase regarding the microcontroller. We are evaluating whether an ESP32 provides enough processing power for real-time SLAM or if the project requires a more robust Raspberry Pi/Jetson architecture, which significantly increases the unit cost.

Power Optimization: Designing a battery system small enough to be portable but powerful enough to run a vacuum-grade fan for 2+ hours is a complex engineering hurdle.

Accomplishments that we're proud of

We are proud of the Comprehensive System Design. Moving from a vague idea to a detailed technical roadmap that includes emergency response logic (Alexa integration), AI-based filter prediction, and a mobile-first user experience is a major milestone. We successfully identified a massive gap in the current $12B+ air purifier market and engineered a logical solution to solve the "static air" problem.

What we learned

We learned that "Hardware is Hard." Beyond just writing code, building a physical product requires an understanding of unit economics, supply chains, and power electronics. We realized that a successful startup isn't just about a great idea; it’s about a viable Product-Market Fit and a clear path to manufacturing. We’ve also gained significant experience in IoT protocols and system architecture.

What's next for Void

Our immediate next step is Securing Seed Funding or a student grant to build our first Works-Like Prototype.

Selection of Tech Stack: Finalizing our microcontroller choice based on power-consumption testing.

MVP Assembly: Building a scaled-down version of the chassis to test basic obstacle avoidance logic.

Beta Algorithm: Refining our "Search and Purify" AI algorithm to ensure the robot can identify the "dirtiest" part of a room autonomously.

Share this project:

Updates