Reachy Mini x Strands Agent on Jetson Thor - Part 4: Local Vision with NVIDIA Cosmos Reason 2
· 11 min read
This is Part 4 of the series. In Part 3 the robot learned to listen. Now I want to give it eyes: the ability to look through its camera and answer a question about the room — identify an object, read visible text, count things, or describe what a person is doing — entirely on-device.