People navigating in unfamiliar buildings take advantage of myriad visual, spatial and semantic cues to efficiently achieve their navigation goals. Towards equipping computational agents with similar capabilities, we introduce Pathdreamer, a visual world model for agents navigating in novel indoor environments. Given one or more previous visual observations, Pathdreamer generates plausible high-resolution 360 visual observations (RGB, semantic segmentation and depth) for viewpoints that have not been visited, in buildings not seen during training. In regions of high uncertainty (e.g. predicting around corners, imagining the contents of an unseen room), Pathdreamer can predict diverse scenes, allowing an agent to sample multiple realistic outcomes for a given trajectory. We demonstrate that Pathdreamer encodes useful and accessible visual, spatial and semantic knowledge about human environments by using it in the downstream task of Vision-and-Language Navigation (VLN). Specifically, we show that planning ahead with Pathdreamer brings about half the benefit of looking ahead at actual observations from unobserved parts of the environment. We hope that Pathdreamer will help unlock model-based approaches to challenging embodied navigation tasks such as navigating to specified objects and VLN.
翻译:在不熟悉的建筑中航行的人利用各种视觉、空间和语义提示来有效地实现导航目标。为了装备具有类似能力的计算剂,我们引入了Pathdreamer,这是在新室内环境中航行的代理商的视觉世界模型。根据以往的一个或多个视觉观测,Pathdreamer为没有被访问过的观点生成了可信的高分辨率360视觉观测(RGB,语义分割和深度),在培训期间没有看到这些观点的建筑中。在高度不确定的地区(例如,在角落周围预测,想象一个隐蔽的房间的内容),Pathdreamer可以预测不同的场景,允许一个代理商为某个轨道取样多种现实的结果。我们证明,Pathdreamer通过在愿景和语言导航(VLN)下游任务中使用了有关人类环境的有用和可获取的视觉、空间和语义知识,从而将人类环境的视觉、语言、语言和语言知识编码起来。具体地,我们表明,与Pathdreamer进行规划会给人带来从环境未观测的实际观测带来大约一半的好处。我们希望,路由路德-Nreamer 将帮助解的物体解的导航成为向这样的导航任务。