Flexible pick-and-place is a fundamental yet challenging task within robotics, in particular due to the need of an object model for a simple target pose definition. In this work, the robot instead learns to pick-and-place objects using planar manipulation according to a single, demonstrated goal state. Our primary contribution lies within combining robot learning of primitives, commonly estimated by fully-convolutional neural networks, with one-shot imitation learning. Therefore, we define the place reward as a contrastive loss between real-world measurements and a task-specific noise distribution. Furthermore, we design our system to learn in a self-supervised manner, enabling real-world experiments with up to 25 000 pick-and-place actions. Then, our robot is able to place trained objects with an average placement error of (2.7 $\pm$ 0.2) mm and (2.6 $\pm$ 0.8)$^\circ$. As our approach does not require an object model, the robot is able to generalize to unknown objects while keeping a precision of (5.9 $\pm$ 1.1) mm and (4.1 $\pm$ 1.2)$^\circ$. We further show a range of emerging behaviors: The robot naturally learns to select the correct object in the presence of multiple object types, precisely inserts objects within a peg game, picks screws out of dense clutter, and infers multiple pick-and-place actions from a single goal state.

中文翻译：

---

无对象模型的精确拾取和放置的自监督学习

灵活的取放是机器人技术中一项基本但具有挑战性的任务，特别是由于需要对象模型来定义简单的目标姿势。在这项工作中，机器人学会了根据单个演示的目标状态使用平面操作来拾取和放置物体。我们的主要贡献在于将机器人学习原语（通常由全卷积神经网络估计）与一次性模仿学习相结合。因此，我们将位置奖励定义为真实世界测量值和特定任务噪声分布之间的对比损失。此外，我们将我们的系统设计为以自我监督的方式学习，从而支持多达 25 000 个拾放动作的真实世界实验。然后，我们的机器人能够以平均放置误差为 (2.7$\下午$ 0.2) 毫米和 (2.6 $\下午$ 0.8)$^\circ$. 由于我们的方法不需要对象模型，因此机器人能够泛化到未知对象，同时保持 (5.9$\下午$ 1.1) 毫米和 (4.1 $\下午$ 1.2)$^\circ$. 我们进一步展示了一系列新出现的行为：机器人自然地学会在存在多种物体类型的情况下选择正确的物体，在钉子游戏中精确地插入物体，从密集的杂物中挑出螺丝，并推断出多个拾放动作从单一目标状态。