# Physical AI labeling interfaces

A gallery of labeling and evaluation interfaces built with Label Studio Enterprise programmable interfaces. Each entry is a starting point to adapt, not a fixed template.

**URL:** https://humansignal.com/use-cases/physical-ai

## Physical AI interfaces (2)

### Robotics Episode Review

**Category:** Physical AI  
**URL:** https://humansignal.com/use-cases/robotics-episode-review

Step through a robot policy rollout across multi-camera video, rate execution quality, and refine a timeline of subtasks, mistakes, and subgoals.

A policy rollout is judged on video, but the useful output is a timeline: where each subtask started, where the mistake happened, what the coaching note should say. This interface keeps both in view.

Annotators watch top, wrist, and other camera streams in a single, gallery, or main-plus-side layout, scrub with frame stepping and speed control, and edit segments from the timeline toolbar: add a subtask, split at the playhead, mark a mistake, pin a subgoal. A metadata panel holds the 1 to 5 quality rating, control mode, speed bin, and robot ID.

### LiDAR Object Detection & Tracking

**Category:** Physical AI  
**Data types:** LiDAR, COPC  
**URL:** https://humansignal.com/use-cases/lidar-object-detection-tracking

Annotate 3D point clouds with cuboids, track objects across frames with keyframe interpolation, and review calibrated camera views, all in one task.

Most perception teams annotate the same scene four times: once for cuboids, again for camera views, again for tracking, and once more for review. This interface keeps all of it in one workspace.

Annotators work the 3D point cloud alongside a top-down view and a camera panel that follows whatever cuboid is selected. Keyframe interpolation carries objects across frames, so adjusting one position updates the frames around it instead of redrawing each one — which is where identity swaps usually creep in. Model predictions load as editable suggestions to accept, adjust, or reject. Validation runs inside the task, so blocking errors surface before completion rather than in a separate audit pass weeks later.

Handles COPC files in the tens of millions of points, with cuboids, points, lines, lanes, and segmentation masks side by side.

**Links**
- [Read the Blog](https://humansignal.com/blog/lidar-annotation-label-studio/)

---

Generated from the HumanSignal CMS at build time. HTML version: https://humansignal.com/use-cases/physical-ai