DeepAI AI Chat
Log In Sign Up

Where to Look Next: Unsupervised Active Visual Exploration on 360° Input

by   Soroush Seifi, et al.
KU Leuven

We address the problem of active visual exploration of large 360 inputs. In our setting an active agent with a limited camera bandwidth explores its 360 environment by changing its viewing direction at limited discrete time steps. As such, it observes the world as a sequence of narrow field-of-view 'glimpses', deciding for itself where to look next. Our proposed method exceeds previous works' performance by a significant margin without the need for deep reinforcement learning or training separate networks as sidekicks. A key component of our system are the spatial memory maps that make the system aware of the glimpses' orientations (locations in the 360 image). Further, we stress the advantages of retina-like glimpses when the agent's sensor bandwidth and time-steps are limited. Finally, we use our trained model to do classification of the whole scene using only the information observed in the glimpses.


page 1

page 3

page 4


Sidekick Policy Learning for Active Visual Exploration

We consider an active visual exploration scenario, where an agent must i...

Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration

Active visual exploration aims to assist an agent with a limited field o...

Emergence of Exploratory Look-Around Behaviors through Active Observation Completion

Standard computer vision systems assume access to intelligently captured...

Streaming Scene Maps for Co-Robotic Exploration in Bandwidth Limited Environments

This paper proposes a bandwidth tunable technique for real-time probabil...

Learning Sparse and Meaningful Representations Through Embodiment

How do humans acquire a meaningful understanding of the world with littl...

Active Robotic Mapping through Deep Reinforcement Learning

We propose an approach to learning agents for active robotic mapping, wh...

Efficient Navigation of Active Particles in an Unseen Environment via Deep Reinforcement Learning

Equipping active particles with intelligence such that they can efficien...