orbit-robotics 0.5.4

Data engineering copilot for robot imitation learning datasets

ORBIT — Data Quality Analysis for Robot Policy Training

Predict whether your robot learning dataset will actually train successfully — before burning GPU hours.

ORBIT analyzes your demonstration data for the issues that cause training failures: dead joints, action divergence, inconsistent demonstrations, poor workspace coverage, and more. Get a quality grade (A-F) and calibrated success prediction based on 82+ ground-truth training outcomes.

Quick Start

pip install orbit-robotics
orbit analyze lerobot/pusht

No GPU required. No API keys required. Works out of the box.

What It Checks

• Quality grade (A-F) calibrated against real training outcomes
• Success prediction — probability your data will train a working policy
• Dead joint detection — finds servos that aren't moving
• Action divergence — detects contradictory demonstrations
• Episode consistency — flags recording issues and length outliers
• Policy fit — rates compatibility with ACT, Diffusion Policy, SmolVLA, OpenVLA
• Workspace coverage — checks if demonstrations cover the task space
• Community comparison — benchmarks against other public datasets

Example Output

Dataset Readiness: B+ (score: 78/100)
Good data — minor issues, should train well

  ✓ High consistency (0.95)
  ✓ Sufficient episodes (200) for diffusion_policy
  ✓ Good coverage (0.84)
  ✗ 2 joints clipping (>10% of frames)

Top action: Fix joint clipping before training

YOUR DATA AT A GLANCE
────────────────────────────────────────
  Episodes:       200     (top 25%)
  Coverage:       0.84  ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░
  Signal Health:  0.92  ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░

(Illustrative — actual output depends on your dataset.)

Optional: AI-Powered Assessment

For deeper analysis using vision-language models:

pip install orbit-robotics[vlm]
export GOOGLE_API_KEY=your-key
orbit analyze lerobot/your-dataset --deep

Uses Gemini for VLM-based visual assessment. The core statistical analysis works fully without any API key.

You can also use Claude as an alternative AI provider:

pip install orbit-robotics[claude]
export ANTHROPIC_API_KEY=your-key

Commands

Command	What it does
orbit analyze <dataset>	Full quality analysis with grade and predictions
orbit benchmark <task>	Compare against published training benchmarks
orbit assist	AI troubleshooter for data and training issues
orbit suggest <dataset>	Training command with tuned hyperparameters
orbit clean <dataset>	Remove bad episodes automatically
orbit fix <dataset>	Analyze, clean, and suggest in one shot

Common Options

orbit analyze lerobot/my-dataset --policy act       # Check fit for specific policy
orbit analyze lerobot/my-dataset --deep              # AI-powered deep analysis (needs GOOGLE_API_KEY)
orbit analyze lerobot/my-dataset --json              # Machine-readable output
orbit analyze lerobot/my-dataset --full              # All episodes (no sampling)
orbit analyze ./local-data/ --format hdf5            # Local HDF5 files

Supported Formats

Format	Source
LeRobot (Hub)	HuggingFace datasets (lerobot/...)
LeRobot (local)	Local LeRobot directories
HDF5	RoboMimic, robosuite, custom .hdf5 files
RLDS	TFRecord-based datasets (pip install orbit-robotics[rlds])
ROS bags	.bag and .mcap files (pip install orbit-robotics[rosbag])

Understanding Grades

Grade	Score	Meaning
A	85-100	Ready to train — expect strong results
B	72-84	Good data — minor issues, should train well
C	58-71	Usable but has problems — clean first
D	40-57	Significant issues — collect more or better data
F	0-39	Critical problems — fix before training

Grades are calibrated against 82 real datasets with known training outcomes.

Requirements

• Python 3.10+
• No GPU needed
• No API keys needed for core analysis

License

MIT