Event
EgoWAM Replaces Action Retargeting with World-State Supervision for Dual-Arm Manipulation Learning
1 reports · 1 sources
EgoWAM addresses a practical contradiction in dual-arm robot manipulation learning: first-person data collected by Project Aria glasses is cheap and abundant, but retargeting human hand trajectories into robot actions and then performing behavior cloning (BC) is difficult; therefore, this work switches the supervision channel from actions to world states.
Report timeline
- EgoWAM Switches the Supervision Channel for Dual-Arm Manipulation from Actions to World State
EgoWAM examines a concrete deployment conflict in dual-arm robotic manipulation: first-person human data collected by Project Aria glasses is cheap and abundant, but retargeting human hand trajectories into robot actions for behavior cloning (BC) is difficult, so this work switches the supervision channel from actions to world state.
Guyuehome ·