AI & ML interests
None defined yet.
Recent Activity
HiveBoard: An Open, Modular, 3D‑Printed Benchmark of Industrial Mechanisms for Robotic and Prosthetic Manipulation
What is HiveBoard?
HiveBoard is a fully 3D-printed, open benchmark for evaluating grippers, hands, and manipulation policies on functional mechanisms — valves, locks, drawers, switches, threaded fasteners — instead of loose, free-floating objects.
A hexagonal honeycomb base accepts 12 interchangeable attachments, grouped into three skill categories:
| Category | Examples |
|---|---|
| 🔧 Torque-based | Ball valve, gate valves, circuit breaker, light bulb |
| 🎯 Precision-based | Threaded fasteners, peg insertion, button |
| 🧩 Composed assembly | Lock & key, drawer, shock absorber |
Every attachment prints on a consumer-grade FDM printer and ships with articulated URDF/USD assets for direct use in simulators like MuJoCo and Isaac Sim.
Why contribute?
Manipulation research keeps benchmarking on grasping loose objects — HiveBoard is built to cross-validate real embodiments (arms, legged manipulators, prosthetic hands) on the same functional tasks, so results are comparable across labs, not just within one.
🤝 Join as a contributing lab
We're growing a shared, cross-laboratory evaluation dataset. Contributing is simple:
- Register your lab → Registration form (link do Google Forms aqui)
- Receive your lab's contribution credentials
- Print the board, run the evaluation protocol on your own hardware, and submit your runs
License & data
Evaluation data submitted to this project is released under CC BY 4.0. See the registration form for full licensing and privacy terms.
Questions?
Open an issue on our GitHub or reach out to ricardo.godoy@usp.br.