STORM：基于搜索的生成世界模型用于机器人操作
STORM: Search-Guided Generative World Models for Robotic Manipulation
AI总结：
STORM通过结合生成模型与搜索算法，实现了机器人操作中的时空推理，显著提升了任务成功率和环境适应能力。
摘要：
我们提出了STORM（基于搜索的生成世界模型），一种新的框架，用于机器人操作中的时空推理，该框架统一了基于扩散的动作生成、条件视频预测和基于搜索的规划。与之前的视觉-语言-动作（VLA）模型不同，STORM将规划建立在显式的视觉回放上，使决策具有可解释性和前瞻性。基于扩散的VLA策略提出多样化的候选动作，生成视频世界模型模拟其视觉和奖励结果，蒙特卡洛树搜索（MCTS）通过前瞻评估选择性地细化计划。在SimplerEnv操作基准测试中，STORM实现了新的最先进的平均成功率51.0%，优于强基线如CogACT。奖励增强的视频预测显著提高了时空保真度和任务相关性，将Fréchet视频距离降低超过75%。此外，STORM表现出稳健的重新规划和失败恢复行为，突显了基于搜索的生成世界模型在长周期机器人操作中的优势。
英文摘要：
We present STORM (Search-Guided Generative World Models), a novel framework for spatio-temporal reasoning in robotic manipulation that unifies diffusion-based action generation, conditional video prediction, and search-based planning. Unlike prior Vision-Language-Action (VLA) models that rely on abstract latent dynamics or delegate reasoning to language components, STORM grounds planning in explicit visual rollouts, enabling interpretable and foresight-driven decision-making. A diffusion-based VLA policy proposes diverse candidate actions, a generative video world model simulates their visual and reward outcomes, and Monte Carlo Tree Search (MCTS) selectively refines plans through lookahead evaluation. Experiments on the SimplerEnv manipulation benchmark demonstrate that STORM achieves a new state-of-the-art average success rate of 51.0 percent, outperforming strong baselines such as CogACT. Reward-augmented video prediction substantially improves spatio-temporal fidelity and task relevance, reducing Frechet Video Distance by over 75 percent. Moreover, STORM exhibits robust re-planning and failure recovery behavior, highlighting the advantages of search-guided generative world models for long-horizon robotic manipulation.
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。
