We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision. Map-based memory provides important contextual information for visual navigation, and exhibits unique spatial structure mainly composed of flat walls and rectangular obstacles. Our adaptation approach encourages the inherent regularities on the estimated maps to guide the agent to overcome the prevalent domain discrepancy in a novel environment. Specifically, we propose an efficient learning curriculum to handle the visual and dynamics corruptions in an online manner, self-supervised with pseudo clean maps generated by style transfer networks. Because the map-based representation provides spatial knowledge for the agent's policy, our formulation can deploy the pretrained policy networks from simulators in a new setting. We evaluate MoDA in various practical scenarios and show that our proposed method quickly enhances the agent's performance in downstream tasks including localization, mapping, exploration, and point-goal navigation.
翻译:我们建议了一种领域适应方法,即MADA,该方法使一个经过预先训练的装饰剂适应没有地面真相监督的新的、吵闹的环境。基于地图的记忆为视觉导航提供了重要的背景信息,并展示了主要由平板墙和矩形障碍组成的独特的空间结构。我们的适应方法鼓励了估计地图的内在规律性,以指导代理人在新的环境中克服普遍存在的域差异。具体地说,我们建议了一个高效的学习课程,以在线方式处理视觉和动态腐败,由风格传输网络生成的假的清洁地图进行自我监督。由于基于地图的代表为代理人的政策提供了空间知识,我们的设计可以在新的环境中从模拟器中部署预先训练的政策网络。我们在各种实际情景中评估MODA,并表明我们提出的方法迅速增强了代理人在下游任务(包括本地化、绘图、勘探和定向导航)中的绩效。