TeleopHardware: MaxRoadmap scaffold
Voice-activated control (ROSA)
Natural-language robot control via on-device LLM + ROS2.
Lab runtime / TeleopOK / VIS-01
Voice-activated control (ROSA) runs against the same observable edge stack used for testing and deployment.
This entry is a roadmap scaffold, not a finished demo. Its description records intended scope; the linked repository is the source of truth for current code.
About this demo
On-device speech-to-text → LLM → ROS2 action. Say 'patrol the warehouse' or 'pick up the box on the left' and the brain routes the intent to the right behavior. Inspired by NASA JPL's ROSA and JetBot voice copilot.
Highlights
- →On-device Whisper STT
- →Local LLM intent parsing
- →ROS2 action dispatcher
- →Wake-word + push-to-talk
Supported robots
Mobile robotsQuadrupedsArms