MIND-V：基于强化学习物理对齐的长期机器人操作分层世界模型
MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment
AI总结：
提出MIND-V分层世界模型，通过语义推理、行为语义桥接和运动视频生成，结合强化学习物理对齐，实现长期机器人操作视频的物理合理合成。
摘要：
可扩展的具身智能受到多样化、长期机器人操作数据稀缺的限制。现有视频世界模型仅能合成简单动作的短视频，且常依赖手动定义轨迹。为此，我们提出MIND-V，一种认知分层世界模型，旨在合成物理合理且逻辑连贯的长期机器人操作视频。受认知科学启发，MIND-V通过三个核心组件桥接高层推理与像素级合成：语义推理中心（SRH）利用预训练视觉语言模型进行任务规划；行为语义桥（BSB）将抽象指令转换为域不变表示；运动视频生成器（MVG）用于条件视频渲染。MIND-V采用分阶段视觉未来展开（Staged Visual Future Rollouts）这一测试时优化策略以增强长期鲁棒性。为强制遵循物理定律，我们引入GRPO强化学习后训练阶段，由新颖的物理预见一致性（PFC）奖励引导。PFC利用V-JEPA2世界模型作为物理裁判，在潜在特征空间中惩罚不合理动态。实验证实MIND-V在长期模拟中的SOTA性能及其对策略学习的重要价值，为具身数据合成引入了可扩展且完全自主的框架。
英文摘要：
Scalable embodied intelligence is constrained by the scarcity of diverse, long-horizon robotic manipulation data. Existing video world models in this domain are limited to synthesizing short clips of simple actions and often rely on manually defined trajectories. To this end, we introduce MIND-V, a cognitive hierarchical world model designed to synthesize physically plausible and logically coherent videos of long-horizon robotic manipulation. Inspired by cognitive science, MIND-V bridges high-level reasoning with pixel-level synthesis through three core components: a Semantic Reasoning Hub (SRH) that leverages a pre-trained vision-language model for task planning; a Behavioral Semantic Bridge (BSB) that translates abstract instructions into domain-invariant representations; and a Motor Video Generator (MVG) for conditional video rendering. MIND-V employs Staged Visual Future Rollouts, a test-time optimization strategy to enhance long-horizon robustness. To enforce adherence to physical laws, we introduce a GRPO reinforcement learning post-training phase guided by a novel Physical Foresight Coherence (PFC) reward. PFC leverages the V-JEPA2 world model as a physics referee to penalize implausible dynamics in the latent feature space. Experiments confirm MIND-V's SOTA performance in long-horizon simulation and its significant value for policy learning, introducing a scalable and fully autonomous framework for embodied data synthesis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
