Active Visual Navigation in an Unexplored Environment

这个项目将开发一种新的机器人导航方法，在这种方法中，目标可以在比以前更高的抽象级别上指定。这将使用深度学习来对场景布局做出明智的预测，并作为主动观察者导航，其中预测通知行动。其结果将是机器人代理能够在以前未见过的环境中进行有效和高效的导航和操作，并能够通过更像人类的指令控制此类代理。这种能力对于自主机器人在各种重要应用领域是可取的，在某些情况下是必不可少的，包括自动化仓储和自动车辆的高级控制。

This project will develop a new method for robotic navigation in which goals can be specified at a much higher level of abstraction than has previously been possible. This will be achieved using deep learning to make informed predictions about a scene layout, and navigating as an active observer in which the predictions informs actions. The outcome will be robotic agents capable of effective and efficient navigation and operation in previously unseen environments, and the ability to control such agents with more human-like instructions. Such capabilities are desirable, and in some cases essential, for autonomous robots in a variety of important application areas including automated warehousing and high-level control of autonomous vehicles.