> For the complete documentation index, see [llms.txt](https://yall.yassrobotics.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://yall.yassrobotics.com/documentation/tutorials/apriltag-pose-estimation.md).

# AprilTag Pose Estimation

This tutorial fuses Limelight MegaTag2 vision measurements into a WPILib pose estimator, the way `DrivebaseSubsystem` does in YALL's [example project](https://github.com/BroncBotz3481/YALL/tree/main/example).

## 1. Set up the camera offset once

MegaTag needs to know where the camera sits relative to robot center. Do this at construction time:

```java
Pose3d cameraOffset = new Pose3d(Inches.of(5).in(Meters),
                                  Inches.of(5).in(Meters),
                                  Inches.of(5).in(Meters),
                                  Rotation3d.kZero);

limelight = new Limelight("limelight");
limelight.getSettings()
         .withLimelightLEDMode(LEDMode.PipelineControl)
         .withCameraOffset(cameraOffset)
         .save();

poseEstimator = limelight.createPoseEstimator(EstimationMode.MEGATAG2);
```

## 2. Submit robot orientation every loop

MegaTag2 fuses AprilTag detections with your robot's current heading. This only works if you tell the Limelight your heading **every periodic loop, before reading a pose estimate**:

```java
@Override
public void periodic() {
    limelight.getSettings()
             .withRobotOrientation(new Orientation3d(gyro.getRotation3d(),
                                                      new AngularVelocity3d(DegreesPerSecond.of(0),
                                                                            DegreesPerSecond.of(0),
                                                                            DegreesPerSecond.of(0))))
             .save();
    // ...
}
```

{% hint style="warning" %}
Skip this step and MegaTag2 pose estimates will be inaccurate or stale — this is the single most common mistake when adopting MegaTag2. See [How do I choose between MegaTag1 and MegaTag2?](/documentation/how-to-guides/how-do-i-choose-megatag1-vs-megatag2.md)
{% endhint %}

## 3. Read and filter the pose estimate

```java
Optional<PoseEstimate> visionEstimate = poseEstimator.getPoseEstimate();
visionEstimate.ifPresent((PoseEstimate poseEstimate) -> {
    // Reject long-range or ambiguous reads before fusing.
    if (poseEstimate.avgTagDist < 4
        && poseEstimate.tagCount > 0
        && poseEstimate.getMinTagAmbiguity() < 0.3) {
        poseEstimator.addVisionMeasurement(poseEstimate.pose.toPose2d(), poseEstimate.timestampSeconds);
    }
});
```

`poseEstimator` above is your WPILib `SwerveDrivePoseEstimator` / `DifferentialDrivePoseEstimator` — a different object than YALL's `LimelightPoseEstimator`. Filtering on tag count, distance, and ambiguity before calling `addVisionMeasurement` keeps a single noisy or distant reading from corrupting your odometry.

## Alternative: the BotPose enum directly

If you don't need a `LimelightPoseEstimator` instance around, `BotPose` gives the same data directly:

```java
Optional<PoseEstimate> estimate = BotPose.BLUE_MEGATAG2.get(limelight);
```

Or fetch the alliance-relative estimate without checking `DriverStation` yourself:

```java
Optional<PoseEstimate> estimate = poseEstimator.getAlliancePoseEstimate();
```

## Next steps

* [Pose Estimation & Ambiguity](/documentation/understanding/pose-estimation-and-ambiguity.md) — what each `PoseEstimate` field means and how to tune your filter thresholds.
* [How do I mount a Limelight on a moving mechanism?](/documentation/how-to-guides/how-do-i-mount-a-limelight-on-a-moving-mechanism.md) — updating `withCameraOffset` dynamically for a turret.
* [How do I filter AprilTags by ID?](/documentation/how-to-guides/how-do-i-filter-apriltags-by-id.md)
* [AprilTag & MegaTag2 Localization Tuning](/documentation/tuning/apriltag-and-megatag2-tuning.md) — IMU modes, assist alpha, and the setup mistakes that silently break MegaTag2.
* [ChArUco Camera Calibration](/documentation/tuning/charuco-camera-calibration.md) — improves the accuracy of every pose this tutorial produces.


---

# 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://yall.yassrobotics.com/documentation/tutorials/apriltag-pose-estimation.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.