FindView: Precise Target View Localization Task for Look Around Agents
This addresses the need for service robots and automated inspection to localize in environments for better human communication, but it is incremental as it builds on existing tasks and methods.
The authors tackled the problem of precise target view localization for look-around agents, proposing the FindView task and showing that learned methods achieve robust and precise localization, with advantages in handling corruption and deployment in novel scenes.
With the increase in demands for service robots and automated inspection, agents need to localize in its surrounding environment to achieve more natural communication with humans by shared contexts. In this work, we propose a novel but straightforward task of precise target view localization for look around agents called the FindView task. This task imitates the movements of PTZ cameras or user interfaces for 360 degree mediums, where the observer must "look around" to find a view that exactly matches the target. To solve this task, we introduce a rule-based agent that heuristically finds the optimal view and a policy learning agent that employs reinforcement learning to learn by interacting with the 360 degree scene. Through extensive evaluations and benchmarks, we conclude that learned methods have many advantages, in particular precise localization that is robust to corruption and can be easily deployed in novel scenes.