EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models

作者：Yu Bai, MingMing Yu, Chaojie Li, Ziyi Bai, Xinlong Wang, Börje F. Karlsson · 单位：Beijing Academy of Artificial Intelligence · 会议/期刊：arXiv preprint · 方向：导航 · 发布日期：2026-02