Unified streaming embodiment
Bring interaction, navigation and manipulation into a shared architecture. Unified pretraining and a multi-rate runtime connect multimodal representations to speech and whole-body motion.
RESEARCH DIRECTIONS
Exploring how intelligence can understand its environment and participate in it.
Bring interaction, navigation and manipulation into a shared architecture. Unified pretraining and a multi-rate runtime connect multimodal representations to speech and whole-body motion.
Simplex SA0 combines streaming speech and actions with tool use, priority-based events, multi-person interaction and interruption recovery. The full-duplex interaction proof of concept has been tested on High Torque’s Piplus.
Connect who is present, what is happening and what has happened before. Context supports expressive interaction and a persistent agent’s goals across time.
FastCD exposes structured decisions. Voice infrastructure and the Agent Harness support the surrounding workflow, from data and compute management to coding and agent orchestration.