Robotic Information Gathering via Deep Generative Inpainting
Robotic Information Gathering via Deep Generative Inpainting
复制标题
DOI：
10.1109/smc53992.2023.10394444
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Tamim Khatib;O. P. Kreidl;Ayan Dutta;Ladislau Bölöni;Swapnoneel Roy
中科院分区：
文献类型：
--
作者：
Tamim Khatib;O. P. Kreidl;Ayan Dutta;Ladislau Bölöni;Swapnoneel Roy
在当今的自动化时代，移动机器人被用来收集有关环境现象的有意义的信息，例如农田中的温度或湿度分布。文献中的大多数研究都假设底层信息场是高斯分布的，因此，基于高斯过程（GP）的模型非常流行。此外，我们发现，由于这种基于 GP 的技术固有的计算复杂性，文献中的大多数研究都无法扩展到小规模环境之外，即信息点的数量 $n < 1000$。这些使得这种预测模型在许多实际应用中或多或少毫无用处。在本文中，我们假设一种不同的技术，即基于生成对抗网络的修复，对于机器人信息收集可能是有用的。最先进的修复技术 1) 不假设基础数据是高斯分布，2) 轻松扩展到 $n\gg 1000$。因此，它们消除了基于 GP 的解决方案带来的两个瓶颈。我们已经在合成和真实世界作物数据集上测试了我们的假设。结果表明，虽然修复技术很容易扩展到 1024 美元\乘以 1024 美元，但基于 GP 的预测却不能。另一方面，它们的解决方案质量具有可比性。
In today's era of automation, mobile robots are being used for collecting meaningful information about an ambient phenomenon such as temperature or moisture distribution in an agricultural field. Most of the studies in the literature assume that the underlying information field is Gaussian, and therefore, Gaussian Process (GP)-based models are extremely popular. Furthermore, we have found that due to the inherent computational complexity of such naive GP-based techniques, most studies in the literature do not scale well beyond small-size environments, i.e., where the number of informative points $n < 1000$. These render such a predictive model more or less useless in many practical applications. In this paper, we posit that a different technique, Generative Adversarial Network-based inpainting, for robotic information gathering can be useful. The state-of-art inpainting techniques 1) do not assume that the underlying data is Gaussian, and 2) easily scale to $n\gg 1000$. Thus, they eliminate the two bottlenecks posed by the GP-based solutions. We have tested our hypothesis on a synthetic and a real-world crop dataset. Results show that while the inpainting technique easily scales to $1024\times 1024$, GP-based predictions cannot. On the other hand, their solution qualities are shown to be comparable.