← Back to Benchmarks
simmediumsim-to-realmetric · varies
EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots
Description
Humans can rearrange objects in cluttered environments using egocentric perception, navigating occlusions without global coordinates. Inspired by this capability, we study long-horizon multi-object non-prehensile rearrangement for mobile robots using a single egocentric camera. We introduce EgoPush, a policy learning framework that enables egocentric, perception-driven rearrangement without relying on explicit global state estimation that often fails in dynamic scenes. EgoPush designs an object-