Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
Embodied-R1:强化的具身推理用于通用机器人操作
机构 * College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部)
专题命中 视觉空间推理 :reasoning(title,abstract);分类 cs.AI、cs.LG
AI总结 本文提出Embodied-R1,通过引入指向作为统一的中间表示,结合强化微调方法,实现通用机器人操作中的具身推理,展示了在多个基准测试中的卓越性能和零样本泛化能力。
Comments Embodied-R1 technical report v2; Published as a conference paper at ICLR 2026