> ## Documentation Index
> Fetch the complete documentation index at: https://avala.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# தன்னியக்க வாகனங்கள்

> பல-சென்சார் AV தரவை காட்சிப்படுத்தி விளக்கக்குறிப்பிடுங்கள் — கேமராக்கள், LiDAR, ரேடார் மற்றும் MCAP பதிவுகள்

Autonomous vehicle teams produce the largest and most complex sensor datasets in the industry. Avala provides a single platform to visualize raw multi-sensor recordings, annotate perception training data, and run quality control -- without switching between separate visualization and labeling tools.

## Visualization First

Before annotating, AV teams need to explore and understand their data. Avala's multi-sensor viewer handles the full AV sensor stack:

<CardGroup cols={2}>
  <Card title="MCAP Playback" icon="play">
    Upload MCAP recordings from your vehicle fleet and play back all sensor streams in a synchronized multi-panel viewer with 8 panel types.
  </Card>

  <Card title="Surround Camera + LiDAR" icon="camera-cctv">
    View all surround cameras alongside LiDAR point clouds with automatic calibration-aware projection for cross-sensor verification.
  </Card>

  <Card title="GPU-Accelerated 3D" icon="cube">
    Render LiDAR point clouds with WebGPU acceleration and 6 visualization modes: Neutral, Intensity, Rainbow, Label, Panoptic, and Image Projection.
  </Card>

  <Card title="Timeline Navigation" icon="clock">
    Scrub through drive logs, step frame-by-frame, and jump to specific timestamps. All panels stay synchronized across different sensor rates.
  </Card>
</CardGroup>

This means your engineers can use Avala for data review and debugging (replacing Foxglove or Rerun), and your annotation team can label the same data in the same interface.

## Data Types

| Sensor                 | Avala Data Type               | Typical Annotation                                              |
| ---------------------- | ----------------------------- | --------------------------------------------------------------- |
| Front/surround cameras | Image, Video                  | 2D bounding boxes, lane polylines, segmentation masks           |
| LiDAR                  | Point Cloud                   | 3D cuboids with heading, dimensions, and tracking IDs           |
| Radar                  | MCAP (via Point Cloud panels) | 3D cuboids, detection markers                                   |
| Multi-sensor fusion    | MCAP                          | Synchronized camera + LiDAR annotation with 3D-to-2D projection |

## Common Tasks

### 3D Object Detection

Label vehicles, pedestrians, cyclists, and static objects with 3D cuboids in LiDAR point clouds. The 3D annotation editor provides bird's-eye, perspective, and side views for precise cuboid placement. Cuboids include full position (x, y, z), dimensions (length, width, height), and heading (yaw) parameters.

### Multi-Camera Projection

Annotate 3D cuboids in the LiDAR view and automatically project them onto surround camera images for visual verification. The viewer supports both pinhole and double-sphere camera models, so projection works with standard and fisheye lenses.

<Tip>
  Multi-camera projection is one of the most effective ways to verify 3D annotation quality. Depth and heading errors that are hard to spot in a top-down view become obvious when the cuboid is overlaid on the camera image.
</Tip>

### Lane and Road Boundary Annotation

Use polyline tools to trace lane markings, curbs, and road edges in camera views. Polylines support connected segments with vertex-level editing, making them suitable for curved lanes and complex intersections.

### Temporal Object Tracking

Track objects across frames with consistent IDs for motion prediction and trajectory forecasting models. Object IDs persist across the sequence timeline, and the viewer's frame-by-frame navigation makes it straightforward to verify tracking continuity.

### Scene Classification

Classify driving conditions at the scene level -- weather (clear, rainy, foggy), time of day (daytime, dusk, nighttime), road type (highway, urban, rural), and traffic density. Classification labels apply to the entire frame and can be combined with object-level annotations.

## Avala Features Used

| Feature                      | Purpose                                                          | Learn More                                                     |
| ---------------------------- | ---------------------------------------------------------------- | -------------------------------------------------------------- |
| MCAP / ROS integration       | Ingest multi-sensor recordings from your vehicle fleet           | [MCAP & ROS](/docs/visualization/mcap-ros/overview)                 |
| Multi-sensor viewer          | Synchronized playback of cameras, LiDAR, radar, and IMU          | [Multi-Sensor Viewer](/docs/visualization/multi-sensor-viewer)      |
| GPU-accelerated point clouds | Inspect LiDAR data with 6 visualization modes                    | [Visualization Overview](/docs/visualization/overview)              |
| 3D cuboid annotation         | Label objects in 3D with bird's-eye, perspective, and side views | [3D Cuboid Tool](/docs/annotation/guides/tools/cuboid-3d)           |
| Object tracking              | Consistent IDs across frame sequences                            | [Video Annotation](/docs/annotation/tutorials/video-annotation)     |
| Polyline annotation          | Trace lanes, curbs, and road boundaries                          | [Polyline Tool](/docs/annotation/guides/tools/polyline)             |
| Multi-camera projection      | Project 3D annotations onto camera images                        | [Multi-Camera Setup](/docs/visualization/guides/multi-camera-setup) |
| Batch auto-labeling          | Bootstrap annotations with model predictions                     | [Batch Auto-Labeling](/docs/integrations/batch-auto-labeling)       |
| Quality control              | Multi-stage review workflows                                     | [Quality Control](/docs/annotation/guides/quality-control)          |
| Cloud storage                | Connect S3 buckets for large driving datasets                    | [Cloud Storage](/docs/integrations/cloud-storage)                   |

## Example Pipeline

```
Raw sensor data (MCAP recordings from vehicle fleet)
  -> Upload to Avala via cloud storage integration (S3)
  -> Explore recordings in multi-sensor viewer
  -> Verify calibration with LiDAR-to-camera projection
  -> Create annotation project with 3D cuboid + tracking task type
  -> Annotators label 3D cuboids with tracking IDs
  -> Auto-label next batch with model predictions (batch auto-labeling)
  -> QC review with multi-stage workflow
  -> Export in KITTI, COCO, or custom format
  -> Train perception model
  -> Use model predictions for next round of auto-labeling
```

## Getting Started

<Steps>
  <Step title="Upload your drive data">
    Create a dataset with `mcap` data type and upload MCAP recordings from your fleet. For large datasets, use [cloud storage integration](/docs/integrations/cloud-storage) to connect your S3 bucket directly.
  </Step>

  <Step title="Explore in the viewer">
    Open a recording in the multi-sensor viewer. Verify that camera, LiDAR, and transform data are present. Check calibration by enabling LiDAR-to-camera projection.
  </Step>

  <Step title="Set up your annotation project">
    Create a project with 3D cuboid annotation, define your label taxonomy (vehicle, pedestrian, cyclist, etc.), and configure quality control settings.
  </Step>

  <Step title="Annotate and review">
    Your team annotates 3D cuboids with tracking IDs. Reviewers verify annotations using multi-camera projection to catch depth and heading errors.
  </Step>

  <Step title="Export and train">
    Export labeled data in your preferred format. Use the Python or TypeScript SDK to integrate exports into your training pipeline.
  </Step>
</Steps>

## Next Steps

<CardGroup cols={2}>
  <Card title="MCAP & ROS" icon="robot" href="/docs/visualization/mcap-ros/overview">
    Detailed guide for preparing and uploading multi-sensor recordings.
  </Card>

  <Card title="3D Cuboid Tool" icon="cube" href="/docs/annotation/guides/tools/cuboid-3d">
    How to place, adjust, and track 3D cuboids in the point cloud editor.
  </Card>

  <Card title="Recording Best Practices" icon="circle-check" href="/docs/visualization/guides/recording-best-practices">
    Tips for recording data that visualizes and annotates well.
  </Card>

  <Card title="Quality Control" icon="shield-check" href="/docs/annotation/guides/quality-control">
    Set up multi-stage review workflows for production annotation.
  </Card>
</CardGroup>