Humans naturally exploit haptic feedback during contact-rich tasks like loading a dishwasher or stocking a bookshelf. Current robotic systems focus on avoiding unexpected contact, often relying on strategically placed environment sensors. Recently, contact-exploiting manipulation policies have been trained in simulation and deployed on real robots. However, they require some form of real-world adaptation to bridge the sim-to-real gap, which might not be feasible in all scenarios. In this paper we train a contact-exploiting manipulation policy in simulation for the contact-rich household task of loading plates into a slotted holder, which transfers without any fine-tuning to the real robot. We investigate various factors necessary for this zero-shot transfer, like time delay modeling, memory representation, and domain randomization. Our policy transfers with minimal sim-to-real gap and significantly outperforms heuristic and learnt baselines. It also generalizes to plates of different sizes and weights. Demonstration videos and code are available at https://sites.google.com/view/compliant-object-insertion.

翻译：人类在接触密集任务（如装载洗碗机或整理书架）中自然利用触觉反馈。当前机器人系统专注于避免意外接触，常依赖策略性布置的环境传感器。近期，基于接触的操控策略已在仿真环境中训练并部署到真实机器人上，但这些方法需要某种形式的真实世界适应以弥合仿真到现实的差距，这在某些场景下可能不可行。本文针对将盘子插入带槽支架这一接触密集的家庭任务，在仿真中训练了基于接触的操控策略，该策略无需任何微调即可迁移到真实机器人。我们研究了实现这种零样本迁移所需的关键因素，包括时延建模、记忆表征及域随机化。该策略的仿真-现实差距极小，显著优于启发式方法和学习基线模型，并能泛化至不同尺寸和重量的盘子。演示视频与代码见https://sites.google.com/view/compliant-object-insertion。