Fi0

Fi0 is Feagine Robotics’ research-stage cross-embodiment foundation model. It conditions robot actions on language, vision, world state and an explicit description of the current body, while accepting human demonstrations as inference-time skill context.

Facts

  • Company: Feagine Robotics
  • Type: Robot Foundation Model
  • Positioning: Explicit embodiment conditioning
  • Function: Transfer skills across robot bodies
  • Audience: Robot-learning researchers
  • Status: Development
  • Website: https://feagine.com/en/blog

About

About Fi0

Fi0 separates reusable task and world knowledge from the actions required by a particular robot body. Its embodiment representation describes kinematic topology, geometry, sensing, end effectors, actuation and dynamic state, allowing a shared model to reorganize execution as those properties change. Cross-view learning connects human first-person demonstrations with robot observations without requiring pixel-level correspondence.

The model combines an Embodiment Graph, Cross-view World Encoder, Skill Encoder and World Dynamics Model. A human demonstration can introduce an unfamiliar task during inference, while the dynamics layer predicts the embodiment-conditioned outcome of candidate actions before execution. Feagine is initially studying the approach on single-arm, dual-arm and multi-arm soft robots.

Specifications

  • Product type: Robot AI Platform
  • Status: Development
  • Website: Https://feagine.com/en/blog

Timeline

  • Feagine launches Fi0 model and three tendon-driven manipulators - 2026-08-13 - Product Launch - Fi0 combines language, vision, world state and an explicit robot-embodiment representation, and can accept a human demonstration as skill context during inference without a task-specific parameter update. A01, A02 and A03 scale… - source: prnewswire.com

View timeline