发表机构
The Hong Kong University of Science and Technology; BYD Company Limited（香港科技大学; 比亚迪股份有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SARI通过相位分离联合训练，在仿真中生成多样接近、在真实中采集少量接触交互，实现接触密集操作的高效泛化，减少34.3%真实数据收集时间。
AI 中文摘要
视觉-语言-动作（VLA）模型通常需要昂贵的真实世界演示才能适应接触密集操作任务，尤其是在需要跨物体放置位置泛化时。我们提出SARI（模拟接近，真实交互），一种基于简单洞察的相位分离仿真与真实联合训练框架：空间覆盖和接触物理应从最适合它们的域中获取。具体而言，自由空间接近需要空间多样性但能容忍适度的仿真差距，使其适合合成生成；相反，接触交互需要精确的物理但随物体放置位置变化很小，允许少量真实演示在操作空间内泛化。SARI在逼真的数字孪生中生成多样化的模拟接近，同时在仅少数放置位置收集真实接触交互。在这些相位分段演示上进行后训练，单个策略利用视觉外观对齐和共享的相机相对动作表示无缝拼接模拟接近与真实接触交互——无需显式相位标签或手工编码切换。在五个真实世界接触密集操作任务中，SARI将真实数据收集时间减少34.3%，并在未见放置位置实现27.5%的成功率，而所有全任务仿真-真实基线完全失败（0%）。
英文摘要
Vision-language-action (VLA) models often require costly real-world demonstrations to adapt to contact-rich manipulation tasks, particularly when generalization across object placements is needed. We propose SARI (Simulated Approach, Real Interaction), a phase-split sim-and-real co-training framework built on a simple insight: spatial coverage and contact physics should be acquired from the domains best suited to them. Specifically, free-space approaches require spatial diversity but tolerate modest simulation gaps, making them ideal for synthetic generation; conversely, contact interactions demand accurate physics but vary little across object placements, allowing a few real demonstrations to generalize across the workspace. SARI generates diverse simulated approaches in a photorealistic digital twin while collecting real contact interactions at only a few placements. Post-trained on these phase-segmented demonstrations, a single policy seamlessly stitches simulated approaches with real contact interactions using visual appearance alignment and a shared camera-relative action representation--without explicit phase labels or hand-coded switches. Across five real-world contact-rich manipulation tasks, SARI reduces real-data collection time by 34.3% and achieves 27.5% success at unseen placements, where all full-task sim-real baselines fail completely (0%).
