Sim-to-Real Reinforcement Learning for Deformable Object Manipulation
Sim-to-Real Reinforcement Learning for Deformable Object Manipulation
复制标题
DOI：
--
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
J. Matas;Stephen James;A. Davison
中科院分区：
文献类型：
--
作者：
J. Matas;Stephen James;A. Davison
我们看到近期在刚性物体操作方面取得了很多进展，但与可变形物体的交互明显滞后。由于可变形物体的配置空间很大，使用传统建模方法的解决方案需要大量的工程工作。那么，也许绕过显式建模的需求，转而以端到端的方式学习控制是一种更好的方法？尽管人们对使用端到端机器人学习方法的兴趣日益浓厚，但只有少量工作关注它们在可变形物体操作方面的适用性。此外，由于学习这些端到端解决方案需要大量数据，一个新兴的趋势是在模拟中学习控制策略，然后将其迁移到现实世界。到目前为止，还没有研究探索是否有可能学习和迁移可变形物体策略。我们认为，如果要进一步采用模拟到现实的方法，那么就应该有可能学习与各种各样的物体进行交互，而不仅仅是刚性物体。在这项工作中，我们结合最先进的深度强化学习算法来解决操作可变形物体（特别是布料）的问题。我们在三个任务上评估我们的方法——将毛巾折叠到一个标记处、对角折叠面巾以及将一块布搭在衣架上。我们的智能体在具有域随机化的模拟环境中进行充分训练，然后在没有见过任何真实可变形物体的情况下成功部署到现实世界中。
We have seen much recent progress in rigid object manipulation, but interaction with deformable objects has notably lagged behind. Due to the large configuration space of deformable objects, solutions using traditional modelling approaches require significant engineering work. Perhaps then, bypassing the need for explicit modelling and instead learning the control in an end-to-end manner serves as a better approach? Despite the growing interest in the use of end-to-end robot learning approaches, only a small amount of work has focused on their applicability to deformable object manipulation. Moreover, due to the large amount of data needed to learn these end-to-end solutions, an emerging trend is to learn control policies in simulation and then transfer them over to the real world. To-date, no work has explored whether it is possible to learn and transfer deformable object policies. We believe that if sim-to-real methods are to be employed further, then it should be possible to learn to interact with a wide variety of objects, and not only rigid objects. In this work, we use a combination of state-of-the-art deep reinforcement learning algorithms to solve the problem of manipulating deformable objects (specifically cloth). We evaluate our approach on three tasks --- folding a towel up to a mark, folding a face towel diagonally, and draping a piece of cloth over a hanger. Our agents are fully trained in simulation with domain randomisation, and then successfully deployed in the real world without having seen any real deformable objects.