发表机构
Institute of Automation, Chinese Academy of Sciences (CASIA); Alibaba Group; Amap（中国科学院自动化研究所; 阿里巴巴集团; 高德地图）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出DreamTrue机器人世界模型，通过离线几何校准和反事实后训练解决动作跟随与交互覆盖问题，在AgiBot上实现最优动作跟随，将交互缺陷率降至6.25%，获2026年AgiBot世界挑战赛世界模型赛道第一。
AI 中文摘要
我们提出DreamTrue，这是一种多视角、跨 embodiment（ embodiment 指具身形态）的机器人世界模型，用于实现动作忠实且物理合理的视频预测。在现有机器人数据集上训练此类模型面临两个障碍：校准不精确会损害动作跟随能力，而不成功交互的覆盖有限会使预测偏向成功结果。为提升跨具身形态的动作跟随能力，我们将动作轨迹渲染为图像空间条件，并引入离线几何校准以对齐这些条件与目标视频。为扩大交互覆盖范围，我们引入反事实后训练，修改记录的动作轨迹并在更广泛的动作和接触配置下生成未来视频。为在无配对真实未来的情况下为这些预测提供反馈，我们构建了人工标注的视频数据集，涵盖机器人、物体及交互缺陷，并利用其训练具身视频奖励模型。该模型的分数指导强化学习后训练，以实现更物理合理的交互结果。在AgiBot平台上，DreamTrue实现了最先进的动作跟随性能，同时将人工评估的交互缺陷率从48.12%降至6.25%。值得注意的是，我们的模型在2026年AgiBot世界挑战赛的世界模型赛道中排名第一。项目页面可通过此URL获取。
英文摘要
We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias predictions toward successful outcomes. To improve action following across embodiments, we render action trajectories into image-space conditions and introduce offline geometric calibration to align these conditions with the target videos. To broaden interaction coverage, we introduce counterfactual post-training, modifying recorded action trajectories and generating future videos under a wider range of actions and contact configurations. To provide feedback on these predictions without paired ground-truth futures, we construct a human-annotated video dataset covering robot, object, and interaction defects and use it to train an embodied video reward model. Its scores guide reinforcement-learning post-training toward more physically plausible interaction outcomes. On AgiBot, DreamTrue attains state-of-the-art action following, while reducing the human-assessed interaction defect rate from from 48.12% to 6.25%. Notably, our model ranks first in the world model track of the AgiBot World Challenge 2026. The project page can be found at https://brave-eai.github.io/DreamTrue.
Commentsproject page: https://brave-eai.github.io/DreamTrue; code: https://github.com/brave-eai/DreamTrue
