Learning View and Target Invariant Visual Servoing for Navigation
Yimeng Li,Jana Košecka,Yimeng Li,Jana Košecka
The advances in deep reinforcement learning recently revived interest in data-driven learning based approaches to navigation. In this paper we propose to learn viewpoint invariant and target invariant visual servoing for local mobile robot navigation; given an initial view and the goal view or an image of a target, we train deep convolutional network controller to reach the desired goal. We presen...
