HAN
Humanoid Network Any Robot. Any Task. One Network.
docsComing Soon enter the appComing Soon

A networked learning layer for Physical AI.

Robot learning depends on large and diverse data, yet robot data collection remains expensive and difficult to scale. HanVerse lets anyone contribute egocentric video of everyday tasks and earn HAN tokens, powering the next generation of robot learning. Whitepaper →

01

Capture

Record egocentric video of daily tasks using the HanCapture mobile app. The app guides framing and ensures data quality on-device.

02

Validate

Data is scored for quality, annotated with dense language labels, 6-DoF camera poses, and 3D hand poses (21 keypoints per hand). Provenance is registered on-chain.

03

Earn

Contributors receive HAN tokens based on quality scores, task diversity, scene novelty, and annotation density. Every data ID is a verifiable on-chain asset.

04

Train

Research labs and robotics companies access curated datasets to train generalizable manipulation policies across diverse robot embodiments.

🌎

Dataset

Live

A living dataset of 54,980 egocentric human episodes totaling 1,213 hours across 5,061 tasks. Continuously expanded by contributors worldwide, validated by 4 research labs and 3 industry partners.

54,980 Episodes1,213h 4m Duration5,061 TasksCC BY-SA 4.0
📱

Mobile Capture

Planned

Record everyday tasks. The app guides capture quality, validates on-device, and uploads to HanVerse with dense annotations.

iOSHAN SDKOn-Device QA

HAN Token

Pre-TGE

Contributors earn HAN for validated egocentric data. Quality scores, task diversity, scene novelty, and annotation density determine reward multipliers. Staking unlocks governance.

ERC-20veHAN
🔗

On-Chain Validation

Building

Data provenance, contributor identity, and quality scores registered on-chain as verifiable assets. Every data ID, model checkpoint, and skill module is traceable and tradable.

EASSolidityIPFS
🤖

Model Layer

Research

Research partners access curated datasets to train generalizable manipulation policies. Human-to-robot transfer validated across diverse embodiments.

LeRobotACTDiffusion Policy

Governance

Planned

Token holders govern reward curves, data quality standards, partnership decisions, and protocol upgrades. Physical AI belongs to all, so does its governance.

veHANOn-Chain Voting

Join the Network.

Start earning.

or