Emergence of Exploratory Look-Around Behaviors through Active Observation Completion

Abstract

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 learn observation policies that not only perform the completion task for which they are trained, but also generalize to exhibit useful "look-around" behavior for a range of active perception tasks.

arXiv commentMain paper 7 figures, supplementary 6 figures. Published in Science Robotics 2019

References in corpus (6)

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• End to End Learning for Self-Driving Cars
• Deep Convolutional Inverse Graphics Network
• Building Generalizable Agents with a Realistic and Rich 3D Environment
• Unifying Map and Landmark Based Representations for Visual Navigation
• Learning Exploration Policies for Navigation

Cited by in corpus (8)

• Where to Look Next: Unsupervised Active Visual Exploration on 360° Input
• Environment Predictive Coding for Embodied Agents
• SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
• MetaView: Few-shot Active Object Recognition
• Visual Attention in Imaginative Agents
• Towards Embodied Scene Description
• Teaching Perception
• Full-Body Visual Self-Modeling of Robot Morphologies