论文标题
视觉SIM到现实传输的基准测试域随机化
Benchmarking Domain Randomisation for Visual Sim-to-Real Transfer
论文作者
论文摘要
域随机化是一种非常流行的机器人技术传输方法，因为它的简单性和实现传递的能力而没有任何现实世界图像。尽管如此，必须做出许多设计选择才能实现最佳转移。在本文中，我们对这些不同选择进行了全面的基准测试研究，并对现实世界对象姿势估计任务进行了两个关键实验。首先，我们研究渲染质量，发现少数高质量的图像优于大量低质量图像。其次，我们研究了随机化的类型，发现干扰因素和纹理对于对新环境的概括都很重要。
Domain randomisation is a very popular method for visual sim-to-real transfer in robotics, due to its simplicity and ability to achieve transfer without any real-world images at all. Nonetheless, a number of design choices must be made to achieve optimal transfer. In this paper, we perform a comprehensive benchmarking study on these different choices, with two key experiments evaluated on a real-world object pose estimation task. First, we study the rendering quality, and find that a small number of high-quality images is superior to a large number of low-quality images. Second, we study the type of randomisation, and find that both distractors and textures are important for generalisation to novel environments.
