几何变化下机器人插入的视觉仿真到现实学习：应用于钢筋安装
Visual Sim-to-Real Learning for Robotic Insertion under Geometric Variations: Application to Rebar Installation
- University of Washington（华盛顿大学）
- McGill University（麦吉尔大学）
- Princeton University（普林斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对钢筋安装中几何变化下的接触丰富插入任务，提出RebarSim视觉仿真到现实系统，通过教师-学生蒸馏和域随机化实现零样本迁移，在真实机器人上达到91.3%成功率。
AI中文摘要：
钢筋插入是建筑工地上最重复且体力要求最高的任务之一，也是一个在1.4毫米间隙下的接触丰富问题。然而，零件在两个层面上存在变化：每个结构构件的标称设计，以及围绕每个标称设计的制造公差。因此，随着设计和批次的变化，现实世界的数据必须重新收集。我们提出了RebarSim，一个完全在仿真中训练的视觉仿真到现实系统。一个基于特权的状态教师通过强化学习在程序化生成的钢筋几何形状上进行训练，然后被蒸馏到一个多视图学生中，该学生在广泛的域随机化下直接将原始RGB和本体感觉映射到动作。学生零样本迁移到现实世界，在真实工厂生产批次中取出的钢筋在91.3%的真实机器人滚动中成功就位。在这一结果背后，几何多样性和预训练都带来了好处。在多样化的标称设计集上训练，而不是单一设计，提升了教师和学生在新颖设计上的零样本成功率，并且学生策略在其专属设计上优于单一设计专家。预训练的学生适应新设计所需的蒸馏样本比从头训练的学生少4-6倍。视觉仿真到现实的迁移依赖于外观随机化和DAgger混合：移除其中任何一个都会急剧降低成功率。视频、代码和任务资产可在以下网址获取：此https URL。
英文摘要：
Rebar insertion is among the most repetitive and physically demanding tasks on construction sites, and a contact-rich problem at 1.4 mm clearance. The parts, however, vary at two levels: a nominal design per structural member, and fabrication tolerance around each nominal design. Real-world data therefore has to be re-collected as designs and batches change. We present RebarSim, a visual sim-to-real system trained entirely in simulation. A privileged state-based teacher is trained with reinforcement learning over procedurally generated rebar geometries, then distilled into a multi-view student that maps raw RGB and proprioception directly to actions under extensive domain randomization. The student transfers to the real world zero-shot, seating rebars taken from a real factory production run in 91.3% of real-robot rollouts. Underlying that result, geometry diversity and pretraining both bring benefits. Training across a diverse set of nominal designs rather than one lifts the zero-shot success of both the teacher and the student on unseen designs, and the student policy outperforms a single-design specialist on that specialist's own design. A pretrained student then adapts to a new design with 4--6x fewer distillation samples than one trained from scratch. Visual sim-to-real transfer depends on appearance randomization and the DAgger mixture: removing either one sharply lowers success. Videos, code, and task assets are available at https://rebarsim.github.io.
