Pinned
Adding a head-mounted camera is #1 requested features for UMI, but “just adding a camera” is harder than it looks🙃
First, just adding it actually hurts performance (a lot!) due to a much bigger embodiment gap -- the camera now sees more of the body, human neck motion differs
Can we learn whole-body mobile manipulation directly from human demonstrations?
Introducing Whole-Body Mobile Manipulation Interface (HoMMI)
Egocentric + UMI, 0 teleop -> bimanual & whole-body manipulation, long-horizon navigation, active perception
hommi-robot.github.io
00:00









