Sidekick Policy Learning for Active Visual Exploration

By Santhosh K. Ramakrishnan, Kristen Grauman. 2018

30 citations recorded by the source corpus.

We consider an active visual exploration scenario, where an agent must intelligently select its camera motions to efficiently reconstruct the full environment from only a limited set of narrow field-of-view glimpses. While the agent has full observability of the environment during training, it has only partial observability once deployed, being constrained by what portions it has seen and what camera motions are permissible. We introduce sidekick policy learning to capitalize on this imbalance of observability. The main idea is a preparatory learning phase that attempts simplified versions of the eventual exploration task, then guides the agent via reward shaping or initial policy supervision. To support interpretation of the resulting policies, we also develop a novel policy visualization technique. Results on active visual exploration tasks with \(360^{\circ }\) scenes and 3D objects show that sidekicks consistently improve performance and convergence rates over existing methods. Code, data and demos are available (Project website: http://vision.cs.utexas.edu/projects/sidekicks/).

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, background): “Scene completion Past work in scene completion focuses on pixelwise reconstruction of 360 panoramas with limited glimpses [28,50,51,61], inpainting [49,26,35], and inferring unseen 3D structure and semantics [68,78].”
An Exploration of Embodied Visual Exploration (2020, unknown): “exploration methods have been evaluated from different perspectives such as overcoming sparse rewards [49,11], pixelwise reconstruction of environments [33,53,54,61], area covered in the environment [16,15], object interactions [50,27], or as an information gathering phase to solve downstream tasks ”
Emergence of exploratory look-around behaviors through active observation completion (2019, background): “The sidekicks then guide the agent to visit information hot spots in the environment or sample information-rich trajectories while accounting for the fact that observability is only partial during testing (24).”