Raspberry Pi AI project ideas: 5 Award-winning builds to try

If you’ve been thinking about building a Raspberry Pi AI project, why not start now? With the right software and a Raspberry Pi, you can turn everyday devices—like your fridge or office gadgets—into smart, AI-powered tools.

Whether you're looking to automate your home, build a personal assistant, or rethink waste management, these Raspberry Pi project ideas will spark your creativity and level up your skills.

We've rounded up the top 5 AI-driven projects created by the Viam community for our inaugural challenge. Let’s see what they built.

1. Raspberry Pi for home automation

‍

Ever dreamed of a smart desk that responds to your needs? This Raspberry Pi home automation project does just that by integrating machine learning (ML) and robotics to create a contextual lighting system.

With object detection and addressable LED technology, this smart desk lights up precisely where and when you need it.

Project summary

Shopping list

• Raspberry Pi 4 with 'viam-server'
• Webcam

For the full list of hardware you’ll need, head to the full DEB-Forge tutorial.

Step-by-step instructions

1. Set up the vision system by attaching the physical components and configure the smart machine in the app.
2. Capture images of hand gestures and train a ML model for object detection.

3. Deploy and test the model by integrating a detection camera and configuring Vision and ML Model services.
4. Connect Neopixels to the Raspberry Pi to create the lighting system.
5. Link the vision system to the lighting by writing the main script logic using the Viam SDK.

Tips from the creator

To track hand movements effectively, use an object detection model, like YOLO, rather than a simple classification model. Viam's add-on module for YOLO simplifies deployment, making it a great tool for beginners.

Get the full tutorial for the Raspberry Pi smart desk.

2. Raspberry Pi personal office assistant

Ever find yourself swamped with tasks at work? This Raspberry Pi personal office assistant, Betsy, alleviates this by streamlining tasks, ferrying tools, delivering messages, or providing a dose of entertainment.

By combining various technologies like computer vision (CV), natural language processing (NLP), and robotics control, Betsy can follow people around the office, navigate to set locations, send messages between individuals, and converse with employees.

Project summary

Shopping list

• Raspberry Pi 4 with 'viam-server' installed
• Fully assembled robot featuring a SCUTTLE rover
• Ultrasonic sensors, webcam, touch monitor

For the complete materials list, visit the full tutorial.

Step-by-step instructions

1. Assemble the robot and configure the components.
2. Program the robot’s core functionalities using the Viam Python SDK.
3. Integrate LLMs for speech interaction and message delivery.
4. Deploy the Vision and Motion Services to enable real-time navigation and obstacle detection.

A tip from the creator

This AI project was built for under $300! Use creative, low-cost components and accessible platforms like Viam to achieve great results without a big budget.

Get the full tutorial for the Raspberry Pi personal office assistant.

3. Raspberry Pi AI smart trash system

If you've ever hesitated at the recycling station, unsure whether to toss items into paper, plastic, or general waste, this Raspberry Pi AI project is for you. 

Shadi Naguib's build uses a camera and a bit of AI to help people sort waste accurately.

Project summary

Shopping list

• Any computer, including a Raspberry Pi, running viam-server
• Hugging Face account for accessing AI models
• ESP32 microcontroller
• Arduino IDE

Check out the full list in the smart trash system tutorial.

Step-by-step instructions

1. Set up the object detection model by configuring the camera with Viam’s Vision Service and the YOLOv5 module.

2. Set up ESP32 WebServer by connecting hardware and implementing code. 
3. Write the main automation script logic using the Viam SDK.

A tips from the creator

Shadi said, “Improve the system's accuracy by fine-tuning the AI model or adding new features.” 

My suggestions: add voice commands for more interaction or improve the AI model’s accuracy for better material detection.

Get the full tutorial for the Raspberry Pi AI trash system.

‍4. Raspberry Pi AI companion robot for runners

If you’re a long distance runner, you know that sometimes self-motivation can be tough. That’s why Sir Walter Richardson, a runner themself, created Robo DeMo 1000: a companion robot specifically designed to be your personal cheerleader during the most challenging runs.

Project summary

By integrating CV and text-to-speech technology, this AI-powered robot delivers personalized motivational—or, if needed, demotivational—messages tailored to your pace and performance.

Shopping list

• Raspberry Pi 5 running viam-server

• DC motors, Camera, Sound card, XBOX controller

For more details, check the full tutorial.

Step-by-step instructions

1. Assemble the robot and connect hardware components using the wiring diagram.

2. Configure your machine in the app with all the components and services, including the ML Model Service and Vision Service.

3. Use text-to-speech and ChatGPT modules to deliver personalized motivational messages.

Tips from the creator

Upgrade the robot with advanced facial recognition to adapt messages to the runner's emotional state or enhance obstacle detection using Viam’s CV capabilities.

Learn more about the Raspberry Pi AI companion robot for runners.

5. AI personal assistant featuring Raspberry Pi 4 and LLM models

Looking for an AI assistant that listens and responds? This Raspberry Pi project features an advanced AI assistant powered by large language models (LLMs) using the Gemini API.

Project summary

Shopping list

• Raspberry Pi 4
• Pi camera, USB microphone, USB speaker

Visit the full tutorial for details.

Step-by-Step Instructions

1. Connect to the Raspberry Pi and install viam-server onto the device.
2. Configure your machine’s board and camera in the app.
3. Add CV to the device via Viam’s Vision Service. 
4. Set up the speech module, allowing text to speech from an LLM. 
5. Integrate the Gemini API to build a conversational AI that understands and responds to commands.

A tips from the creator

To improve follow-up questions for image inputs, pass the previous model response in the prompt with your follow-up question for better context.

Check out the full project tutorial.

Build your own Raspberry Pi AI project

Inspired by these Raspberry Pi AI projects? Whether you’re creating a smart home system, automating office tasks, or tackling environmental challenges, Viam and Raspberry Pi make it easier than ever. By taking on projects like these, you’ll master hardware, integrate AI, and build intuitive user interfaces.

Ready to get started? Recreate one of the featured community projects above, or explore more of our Raspberry Pi home automation ideas—like designing a smart security system—to take your skills even further.

Join the Viam community

If you want to share your Raspberry Pi project, network with other passionate individuals, and get direct help from our team of engineers, head to our Discord.

‍

‍

About the Author: Hazal Mestci is an artist and technologist with a focus on hardware and software interaction and a Developer Advocate. Her day-to-day involves coding, designing, wiring hardware, and leading initiatives to engage, educate, and inspire other developers. She holds a masters degree in Computer Science and spends her time building robots and smart machines that highlight autonomous navigation, AI, IoT, sustainability practices and climate tech.