Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

语言和多模态基础模型之所以能获得强泛化，是因为异构数据可在统一形式下对齐，并能规模化训练。本文研究这套方法能否用于机器人操作。难点在于操作数据天然异构、采集昂贵且多样性有限。作者提出基于 Qwen-VL 的 Qwen-RobotManip，从表示、运动和行为三个维度统一对齐多源数据，并用 Human-to-Robot 管道把第一视角手部示范转换为 15 种机器人平台的轨迹。仅依靠公开机器人操作数据和人类视频，作者构建约 38,100 小时的 manipulation corpus，并在扰动鲁棒性、指令跟随、失败恢复和跨具身迁移上观察到泛化。由于标准 benchmark 难以反映预训练质量，论文重点采用 RoboCasa365、LIBERO-Plus、EBench、RoboTwin-Clean2Rand、RoboTwin-IF 和 RoboTwin-XE 等 OOD 设置，并在仿真与 AgileX ALOHA、Franka、UR、ARX 真机上验证模型。

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe can be applied to robotic manipulation to achieve genuine generalization. This is challenging because, unlike text, manipulation data is heterogeneous by nature, expensive to collect, and narrow in diversity, making alignment and scale simultaneously difficult. We present Qwen-RobotManip, a generalizable Vision-Language-Action foundation model built on Qwen-VL. Qwen-RobotManip introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. This alignment capability in turn enables Qwen-RobotManip to absorb manipulation data at a scale that prior training regimes could not sustain. A human-to-robot synthesis pipeline converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline harmonizes heterogeneous datasets. Using only open-source datasets and human videos without proprietary data collection, Qwen-RobotManip constructs a ~38,100-hour pretraining corpus and exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. We find that standard benchmarks fail to capture pretraining quality and instead adopt OOD settings including RoboCasa365, LIBERO-Plus, EBench, RoboTwin-Clean2Rand, RoboTwin-IF, and RoboTwin-XE. Qwen-RobotManip substantially outperforms prior state-of-the-art models, including π0.5, across all OOD settings, ranks 1st in RoboChallenge with a 20% relative improvement, and is validated on real-robot platforms including AgileX ALOHA, Franka, UR, and ARX.