> For the complete documentation index, see [llms.txt](https://guide.petoi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.petoi.com/extensible-modules/petoi-ai-vision-module/custom-petoi-vision-model/getting-started/how-we-teach-a-robot-to-see.md).

# How We Teach a Robot to "See"

Before we jump into the technical steps, it helps to understand exactly what we are trying to achieve. Our goal is to give the Petoi robot dog Computer Vision the ability to look at the real world, recognize objects or gestures, and react to them.

To do this, we cannot just write a standard line of code that says "look for an apple." Instead, we have to *teach* the computer what an apple looks like by showing it many examples.

## How It All Connects

Think of this process like teaching a child with flashcards. Here is the step-by-step breakdown of how the system works together:

{% stepper %}
{% step %}

### The Dataset (The Flashcards)

We gather hundreds of images of what we want the robot to recognize.
{% endstep %}

{% step %}

### The AI Model (The Brain)

A computer studies the dataset to learn the patterns, saving the result into a file called a "Model."
{% endstep %}

{% step %}

### SenseCraft (The Bridge)

We use this software platform to take that Model and push it onto the camera's memory.
{% endstep %}

{% step %}

### Petoi Camera (The Eyes)

Equipped with its new "brain," the camera looks at the world, recognizes objects, and tells the dog how to react.
{% endstep %}
{% endstepper %}

## Key Terms You Need to Know

If you are new to Artificial Intelligence, you will see a few terms repeated throughout this guide. Here is a quick reference guide to help you along the way:

<table><thead><tr><th width="228.22216796875">Term</th><th>Definition</th></tr></thead><tbody><tr><td>Computer Vision (AI)</td><td>Technology focused on training computers to interpret and understand the visual world through cameras, much like human eyesight.</td></tr><tr><td>Dataset</td><td>A large collection of data used to teach an AI (e.g., a folder with 500 pictures of different hands making a "Stop" gesture).</td></tr><tr><td>AI Model</td><td>The mathematical "brain" created after the AI studies the dataset. Uploading the model means transferring this brain to the camera.</td></tr><tr><td>Petoi Camera</td><td>The physical vision sensor module that processes the video feed, identifies objects, and sends commands to the robot dog's motherboard.</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://guide.petoi.com/extensible-modules/petoi-ai-vision-module/custom-petoi-vision-model/getting-started/how-we-teach-a-robot-to-see.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.