A crucial capability of real-world intelligent agents is their ability to plan a sequence of
actions to achieve their goals in the visual world. In this work, we address the problem of …

Embodied computer vision considers perception for robots in novel, unstructured
environments. Of particular importance is the embodied visual exploration problem: how …

It is common to implicitly assume access to intelligently captured inputs (eg, photos from a
human photographer), yet autonomously capturing good observations is itself a major …

Passive visual systems typically fail to recognize objects in the amodal setting where they
are heavily occluded. In contrast, humans and other embodied agents have the ability to …

Visual recognition systems mounted on autonomous moving agents face the challenge of
unconstrained data, but simultaneously have the opportunity to improve their performance …

We consider artificial agents that learn to jointly control their gripper and camera in order to
reinforcement learn manipulation policies in the presence of occlusions from distractor …

Internet of Things (IoT) is the set of technologies that can interconnect anything, from daily
life objects to more sophisticated networked devices. The IoT paradigm is constantly …

Visual recognition systems mounted on autonomous moving agents face the challenge of
unconstrained data, but simultaneously have the opportunity to improve their performance …

Robotic material perception is an extremely important but challenging problem for industrial
intelligence. The main difficulties come from the fact that the material properties are difficult …

In this brief, we develop a deep reinforcement learning method to actively recognize objects
by choosing a sequence of actions for an active camera that helps to discriminate between …