Voice-activated control (ROSA)

Natural-language robot control via on-device LLM + ROS2.

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

Related demos

View all →

Teleop

CockPit

Predefined teleop dashboard with dual cameras, 3D model, map, and controls.

Open demo →Dashboard

My UI

Drag-and-drop dashboard — every CockPit widget, your layout.

Open demo →Navigation

Missions

Multi-waypoint autonomous patrols with a state-machine orchestrator.

Open demo →