AerialVLN：面向无人机的视觉与语言导航
AerialVLN: Vision-and-Language Navigation for UAVs
AI总结：
本文提出面向无人机室外导航的AerialVLN新任务，构建含25个城市级场景的三维模拟器，并基于CMA给出扩展基线，揭示其与人类表现的显著差距。
摘要：
近年来兴起的视觉与语言导航（VLN）任务在计算机视觉和自然语言处理领域都引起了广泛关注。现有VLN任务是为在地面（无论是室内还是室外）导航的智能体构建的。然而，许多任务需要智能体在空中执行，例如基于无人机的货物配送、交通/安保巡逻和风景游览等。空中导航比地面导航更为复杂，因为智能体需要考虑飞行高度以及更复杂的空间关系推理。为填补这一空白并推动该领域的研究，我们提出了一项名为AerialVLN的新任务，该任务基于无人机并面向室外环境。我们开发了一个三维模拟器，由25个城市级场景的近乎真实图片渲染而成。该模拟器支持连续导航、环境扩展和配置。我们还基于广泛使用的跨模态对齐（CMA）导航方法提出了一个扩展的基线模型。我们发现基线模型与人类表现之间仍存在显著差距，这表明AerialVLN是一项具有挑战性的新任务。数据集和代码可在https://github.com/AirVLN/AirVLN获取。
英文摘要：
Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap and facilitate research in this field, we propose a new task named AerialVLN, which is UAV-based and towards outdoor environments. We develop a 3D simulator rendered by near-realistic pictures of 25 city-level scenarios. Our simulator supports continuous navigation, environment extension and configuration. We also proposed an extended baseline model based on the widely-used cross-modal-alignment (CMA) navigation methods. We find that there is still a significant gap between the baseline model and human performance, which suggests AerialVLN is a new challenging task. Dataset and code is available at https://github.com/AirVLN/AirVLN.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
