Smiling Buddha Open Research
Open Research · Physical AI

The Real-World Layer
for Physical AI.

Real-deployment anchor data, shared benchmarks, and reproducibility standards for embodied intelligence in operational environments. LeRobot-native. Community-run. Open.

Smiling Buddha
By the Numbers · Real-Deployment Layer
18,050+
V1-V3 catalogued
edge cases
238+
Machine types
45+
OEM brands
60+
Live deployment
sites
4
Industrial
verticals live
2
Dated research
publications (Mar 2026)
26
Months of continuous
operation (since Jun 2024)
Real-deployment scale · Every number verifiable on request
What we work on

Four research areas. One shared goal.

Physical AI needs its own data layer, benchmarks, and reproducible baselines. Smiling Buddha builds and publishes them openly, one area at a time.

Datasets

Edge-case libraries

Structured, versioned, LeRobot v2.1 native. Real-deployment anchor data at V1–V3 fidelity.

Browse →Preview corpus · Q4 2026
Benchmarks

Reproducible baselines

Standardised evaluation suites for perception, planning, and long-horizon manipulation in physical environments.

See suite →In preparation · Founding contributors
Methodology

Real-to-Sim Enrichment

A published framework for extending narrow real-world captures into rich simulation training data with V0-V3 validation scoring.

Read paper →Published · v1.0
Tools

Open-source infrastructure

CLIs, converters, and validation tools for physical AI data engineering. LeRobot / ROS 2 / PyTorch compatible.

Get started →v0.1 · Q4 2026 · Waitlist
Featured research

Real-to-Sim Enrichment Framework v1.0

Our flagship methodology publication. Describes how narrow real-world captures can be systematically extended into rich simulation training data, with a V0 → V3 validation taxonomy.

Latest updates

What's shipping now

All updates
Contributors welcome

Want to contribute?

Freelancers, students, PhD candidates, engineers between roles, working professionals — the Edge Case Library is being built by a distributed community. Named recognition. Remote-first.

Join us