On anticipation and perception, we address the recognition of ongoing activity from videos. In particular we focus on long-duration and complex activities and hence propose a new challenging dataset to facilitate the work. On manipulation with perception, we propose an efficient framework for programming a robot to use human tools and evaluate it on a Baxter research robot. Finally, combining perception, anticipation and manipulation, we focus on a block stacking task. We first explore how to guide robot to place a single block into the scene without collapsing the existing structure and later introduce the target stacking task where the agent stacks blocks to reproduce a tower shown in an image. We validate our model on both synthetic and real-world settings.