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:人类自然地利用接触丰富的任务(如装上洗碗机或储存书架)中的偶然反馈。当前机器人系统的重点是避免意外接触,往往依赖战略环境传感器。最近,对接触利用操纵政策进行了模拟培训,并在实际机器人上部署。然而,它们需要某种形式的现实世界适应,以弥补假到现实的差距,这在各种情况下都可能行不通。在本文中,我们培训了一种接触利用操纵政策,模拟接触丰富的家庭任务,即将装载板装到一个空位的持牌者身上,而该持牌者不向真正的机器人进行任何微调。我们调查了这种零发转让的各种必要因素,如时间延迟模型、记忆表示和域随机化。我们的政策转移最小的模拟到现实差距,大大超越了外形和学习的基线。它还对不同尺寸和重量的板块进行了概括。演示视频和代码可在https://sites.google.com/view/uncion-object-Infritionionment上查阅。