Your First Project

Time: ~60 minutes

Before You Begin

What is Viam?

Viam lets you build robotics applications the way you build other software. Viam abstracts away hardware concerns and services for common tasks to enable you to focus on your core robotics application. Declare your hardware in a config, write control logic against well-defined APIs for everything, push updates through a CLI. Viam is the development workflow you’re used to, applied to physical machines.

Viam supports most robotics hardware. If your hardware isn’t on the list, you can add support with a custom module by implementing the appropriate API.

This tutorial uses the simplest work cell (camera + compute) to teach patterns that apply to all Viam applications.

Scenario

You’re building a quality inspection station for a canning line. Cans move past a camera on a conveyor belt. Your system must:

  1. Detect when a can is present
  2. Classify it as PASS or FAIL (identifying dented cans)
  3. Log results for review and analysis
  4. Provide a monitoring dashboard for operators

Tutorial Overview

In this tutorial you will work through a series of tasks that are common to many robotics applications. The techniques you learn here are applicable regardless of what hardware, software, data, or machine learning models you are working with.

PartTimeWhat You’ll Do
Part 1: Vision Pipeline~15 minSet up camera, ML model, and vision service
Part 2: Data Capture~10 minConfigure automatic image capture and cloud sync
Part 3: Control Logic~15 minGenerate module, write inspection logic, test from CLI
Part 4: Deploy a Module~10 minDeploy module, configure detection data capture
Part 5: Productize~10 minBuild monitoring dashboard with Teleop
Full Section Outline

Part 1: Vision Pipeline (~15 min)

Part 2: Data Capture (~10 min)

Part 3: Control Logic (~15 min)

Part 4: Deploy a Module (~10 min)

Part 5: Productize (~10 min)

Get Started

Begin Part 1: Vision Pipeline →