LaWAM: 用于高效动力学感知机器人策略的潜在世界行动模型
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
AI总结：
提出LaWAM模型，通过潜在视觉子目标预测场景变化，实现动力学感知的机器人控制，在多个基准上达到最优或竞争性成功率，且推理延迟低。
摘要：
视觉-语言-行动模型（VLA）利用大规模视觉-语言预训练进行语义机器人控制，但通常缺乏对机器人行动如何改变场景的明确预见。世界行动模型（WAM）通过基于预测的未来条件化策略来解决这一限制，但现有方法通常依赖计算昂贵的视频生成，且存在大量像素级冗余。我们提出LaWAM，一种潜在世界行动模型，通过紧凑的潜在视觉子目标（而非重建的未来视频）向机器人策略暴露预测动力学。LaWAM的核心是一个潜在行动条件化的潜在世界模型（LaWM）。我们通过在预训练视觉基础模型的潜在空间中训练潜在行动模型，并重新利用其前向解码器来预测未来观察特征以描述场景演变，从而获得LaWM。然后，LaWAM基于这些预测的潜在视觉子目标条件化行动生成，以实现动力学感知的机器人控制。LaWAM在LIBERO（98.6%成功率）、RoboTwin（91.22%成功率）和真实世界操作任务中取得了最优或具有竞争力的成功率，同时保持低延迟推理。LaWAM每次行动块预测运行时间为187毫秒，相比像素空间WAM，实现了高达24倍的墙钟延迟降低。
英文摘要：
Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene. World-Action Models (WAMs) address this limitation by conditioning policies on predicted futures, yet existing approaches typically rely on computationally expensive video generation with substantial pixel-level redundancy. We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video. At the core of LaWAM is a latent-action-conditioned Latent World Model (LaWM). We obtain LaWM by training a latent action model in the latent space of a pretrained vision foundation model and repurposing its forward decoder to predict future observation features for scene evolution. LaWAM then conditions action generation on these predicted latent visual subgoals to enable dynamics-aware robot control. LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference. LaWAM runs in 187 ms per action-chunk prediction and achieves up to 24x lower wall-clock latency than pixel-space WAMs.
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。
