Event
OpenAI trains Dactyl robotic hand system for dexterous object manipulation
Key points
- OpenAI published Dactyl, a robotic-hand system trained entirely in simulation and transferred to real-world manipulation.
- The work used a Shadow Dexterous Hand to reposition objects such as blocks and prisms from camera and fingertip observations.
- The project is relevant as an early OpenAI robotics milestone around sim-to-real dexterous manipulation.
Company context
OpenAI develops foundation models, AI products and research systems, with a renewed robotics program focused on general-purpose robotics, robotic data acquisition, perception, simulation and model evaluation in physical environments. Its robotics relevance is model-layer and infrastructure-led rather than OEM-led.
Context
- Company
- OpenAI
- Segment
- Foundation Models
- Event type
- Research Publication
- Geography
- San Francisco · United States