Emergence of exploratory look-around behaviors through active observation completion

By Santhosh K. Ramakrishnan, Dinesh Jayaraman, Kristen Grauman. 2019

46 citations recorded by the source corpus.

A robotic agent learns how to look around novel environments intelligently by directing the camera to best complete its observations. Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to look around: How can an agent learn to acquire informative visual observations? We propose a reinforcement learning solution, where the agent is rewarded for reducing its uncertainty about the unobserved portions of its environment. Specifically, the agent is trained to select a short sequence of glimpses, after which it must infer the appearance of its full environment. To address the challenge of sparse rewards, we further introduce sidekick policy learning, which exploits the asymmetry in observability between training and test time. The proposed methods learned observation policies that not only performed the completion task for which they were trained but also generalized to exhibit useful “look-around” behavior for a range of active perception tasks.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Occupancy Anticipation for Efficient Exploration and Navigation (2020, methodology): “More recent work uses deep learning to learn navigation [79,20,56,41,77,75,59,64] or exploration [48,6,57,28,51] policies in an end-to-end fashion.”