# Vision-Language-Action (VLA) Models

**Vision-Language-Action (VLA)** models bridge the gap between human instruction and robotic action. These models are trained to connect natural language commands with visual input from the robot's camera and translate that understanding into executable motor commands. Instead of needing complex code, a user can simply tell the robot what to do.

For example, a user could say, "Please pick up the blue cup next to the laptop." The VLA model would:

1. **Vision:** Process the camera feed to locate the "blue cup" and the "laptop."
2. **Language:** Understand the intent behind the command "pick up" and the spatial relationship "next to."
3. **Action:** Generate the precise sequence of motor commands (e.g., move arm to coordinates, open gripper, lower arm, close gripper, lift arm) to execute the task.

VLAs make human-robot interaction intuitive and accessible, paving the way for robots in more collaborative and dynamic settings.

<br>


---

# Agent Instructions: 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:

```
GET https://docs.overthereality.ai/over-wiki/physical-ai/physical-ai-foundation-models-for-robotics/vision-language-action-vla-models.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.