Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist robots. However, collecting diverse, high-quality interaction videos, such as clips that clearly show a person's full body and unoccluded interactions with objects, poses a practical barrier to scaling this approach.
초록에서 가져왔습니다. 요약을 준비 중입니다.