> For the complete documentation index, see [llms.txt](https://docs.openmind.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.openmind.com/full-autonomy-guidelines/features/robot-support.md).

# Robot & Simulation Support

Which autonomy features run on which robot, and where simulation differs from hardware.

Not every autonomy feature runs on every robot, and a few behave differently in the [Cloud Simulator](/simulators/cloud-isaac-sim.md) than on physical hardware. This page is the single source of truth for those differences; the feature guides link here rather than repeating the caveats.

Your integration doesn't have to hard-code any of this — the robot tells you what it can do. `GET /status` reports `robot_type`, `use_sim`, `slam_3d_supported`, and `slam_3d_color_supported`, so you can check a capability at runtime and adapt to whatever robot you're talking to.

The columns use each robot's short name — **Go2** is the Unitree Go2 and **M20 Pro** is the Deep Robotics M20 Pro (shown as **M20** in the portal; its `robot_type` is `m20`).

### Support matrix

| Feature                          | Go2 (hardware) | Go2 (sim) | M20 Pro |
| -------------------------------- | :------------: | :-------: | :-----: |
| 2D mapping & navigation          |        ✅       |     ✅     |    ✅    |
| 3D mapping — SLAM / Color / Full |        ❌       |     ✅     |    ✅    |
| 3D navigation                    |        ❌       |     ✅     |    ✅    |
| Patrol (+ scheduling)            |        ✅       |     ✅     |    ✅    |
| Auto-charging                    |        ✅       |     ✅     |    ✅    |

### The key differences

* **3D on Go2 is simulation-only.** A real Go2 supports **2D SLAM only** — its 3D modes (SLAM, Color, and Full) work in the simulator but not on hardware, where the portal simply doesn't offer them. The **M20 Pro** supports 3D everywhere, in the sim and on hardware.
* **Auto-charging works everywhere.** It's available on the Go2 and the M20 Pro, and behaves the same in the simulator as on hardware — so you can rehearse dock-and-resume in the sim.
* **2D mapping, navigation, and patrol are not sim-gated.** They run the same in both places.

> **G1 and Tron:** the Unitree G1 and LimX Tron can be launched in the Cloud Simulator, but the autonomy features above are built around the quadrupeds (Go2, M20 Pro).


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.openmind.com/full-autonomy-guidelines/features/robot-support.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.