论文标题
CALI：基于无监督的域适应性遍历可部署自动导航的遍及域的适应性
CALI: Coarse-to-Fine ALIgnments Based Unsupervised Domain Adaptation of Traversability Prediction for Deployable Autonomous Navigation
论文作者
论文摘要
遍历性预测是自动导航的基本感知能力。不同领域中数据的多样性对感知模型的预测性能施加了显着差距。在这项工作中，我们通过提出一种新颖的粗到细节无监督的域适应性（UDA）模型-Cali来努力减少差距。我们的目的是以高数据效率转移感知模型，消除昂贵的数据标记，并提高适应过程中的概括能力，从易于访问的源源域到各种具有挑战性的目标域。我们证明，粗对齐和细线的组合可以彼此有益，并进一步设计了先进的预先对准过程。这项工作提出的工作桥接了理论分析和算法设计，从而通过易于且稳定的训练，从而为UDA模型提供了有效的UDA模型。我们在几个具有挑战性的领域适应设置中显示了我们提出的模型比多个基线的优势。为了进一步验证我们的模型的有效性，我们将感知模型与视觉计划器相结合，以构建导航系统，并在没有可用的标记数据的复杂自然环境中显示我们模型的高可靠性。
Traversability prediction is a fundamental perception capability for autonomous navigation. The diversity of data in different domains imposes significant gaps to the prediction performance of the perception model. In this work, we make efforts to reduce the gaps by proposing a novel coarse-to-fine unsupervised domain adaptation (UDA) model - CALI. Our aim is to transfer the perception model with high data efficiency, eliminate the prohibitively expensive data labeling, and improve the generalization capability during the adaptation from easy-to-obtain source domains to various challenging target domains. We prove that a combination of a coarse alignment and a fine alignment can be beneficial to each other and further design a first-coarse-then-fine alignment process. This proposed work bridges theoretical analyses and algorithm designs, leading to an efficient UDA model with easy and stable training. We show the advantages of our proposed model over multiple baselines in several challenging domain adaptation setups. To further validate the effectiveness of our model, we then combine our perception model with a visual planner to build a navigation system and show the high reliability of our model in complex natural environments where no labeled data is available.
