arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.02886cs.RO
收藏

用于操作的数据增强

Data Augmentation for Manipulation

University of Michigan(密歇根大学)

Peter Mitrano, Dmitry Berenson

摘要:

深度学习的成功在很大程度上取决于大型数据集的可用性,但在机器人操作中,存在许多学习问题,而这些数据集并不存在。收集这些数据集既耗时又昂贵,因此从小数据集中学习是一个重要的开放问题。在计算机视觉中,一种常见的解决数据缺乏的方法是数据增强。数据增强是通过修改现有样本来创建额外训练样本的过程。然而,由于任务和数据的类型不同,计算机视觉中使用的方法不能很容易地适应操纵。因此,我们提出了一个数据增强方法的机器人操作。我们认为,扩增应该是有效的,相关的,和多样的。我们使用这些原则,正式扩增作为一个优化问题,与来自物理和知识的操纵域的目标函数。该方法将刚体变换应用于几何状态和动作数据的轨迹。我们在两种情况下测试我们的方法:1)学习刚性圆柱体的平面推动动力学,以及2)学习绳索操作的约束检查器。这两种场景具有不同的数据和标签类型,但在这两种场景中,对我们的增强数据进行训练可以显着提高下游任务的性能。我们还展示了我们的增强方法如何用于真实机器人数据,以实现更高效的在线学习。

英文摘要:

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and expensive, and therefore learning from small datasets is an important open problem. Within computer vision, a common approach to a lack of data is data augmentation. Data augmentation is the process of creating additional training examples by modifying existing ones. However, because the types of tasks and data differ, the methods used in computer vision cannot be easily adapted to manipulation. Therefore, we propose a data augmentation method for robotic manipulation. We argue that augmentations should be valid, relevant, and diverse. We use these principles to formalize augmentation as an optimization problem, with the objective function derived from physics and knowledge of the manipulation domain. This method applies rigid body transformations to trajectories of geometric state and action data. We test our method in two scenarios: 1) learning the dynamics of planar pushing of rigid cylinders, and 2) learning a constraint checker for rope manipulation. These two scenarios have different data and label types, yet in both scenarios, training on our augmented data significantly improves performance on downstream tasks. We also show how our augmentation method can be used on real-robot data to enable more data-efficient online learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑