通过推理时仿真器在环优化实现鲁棒的布料操作
Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement
AI总结：
提出基于仿真器在环优化的布料操作框架，通过合成数据训练的真实到仿真模块和稀疏网格滚动结合先验引导MPPI，从单RGB输入实现鲁棒操作。
摘要：
仿真器在环优化为机器人操作提供了一种有前景的推理时机制。它使用物理仿真器作为后端滚动引擎，并行评估候选轨迹并在线优化标称动作，这种范式在状态和接触相对易处理的刚体操作中已被证明有效。我们通过三个支柱将该范式推广到基于单RGB输入的真实世界布料操作。(i) 我们设计了一个可扩展的合成数据生成和推理时滚动流水线，构建在FLASH（一个可变形物体仿真器）之上，该仿真器在物理保真度、数值稳定性和滚动效率之间提供了实用的平衡。(ii) 我们开发了一个纯合成数据训练的真实到仿真模块，通过融合预训练视觉特征与可学习规范令牌，将单RGB观测映射到仿真兼容的布料状态。(iii) 我们通过将稀疏网格滚动后端与先验引导的MPPI（锚定于离线蒸馏的策略轨迹）耦合进行在线规划，在保留操作相关变形和接触的同时实现足够的并行滚动批次。真实机器人实验表明，与基线方法相比，该方法具有更高的成功率和更强的鲁棒性。
英文摘要：
Simulator-in-the-loop optimization offers a promising inference-time mechanism for robot manipulation. It uses a physical simulator as a backend rollout engine to evaluate candidate trajectories in parallel and refine nominal actions online, a paradigm shown to be effective in rigid-body manipulation where state and contact are relatively tractable. We bring this paradigm to real-world cloth manipulation from a single RGB input through three pillars. (i) We design a scalable synthetic-data generation and inference-time rollout pipeline built on FLASH, a deformable-object simulator that provides a practical balance among physical fidelity, numerical stability, and rollout efficiency. (ii) We develop a real-to-sim module, trained purely on synthetic data, that maps a single RGB observation to simulation-compatible cloth state by fusing pretrained visual features with learnable canonical tokens. (iii) We perform online planning by coupling a sparse-mesh rollout backend with prior-guided MPPI, anchored at an offline-distilled policy trajectory, preserving manipulation-relevant deformation and contact while enabling sufficient parallel rollout batches. Real-robot experiments show higher success rates than baseline methods and closed-loop correction under mid-fold perturbations. Project page: https://silr-cloth.github.io/
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。
