Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation

TL;DR

This paper introduces a learning framework for embodied visual navigation agents to actively ask for help when searching for objects, improving efficiency and robustness in scenarios with intermittent feedback.

Contribution

It proposes a novel training curriculum and uncertainty measure enabling agents to effectively ask for help and handle situations with missing feedback.

Findings

Agents learn to ask for help effectively.

Robustness to absence of feedback is improved.

Empirical results validate the approach.

Abstract

In reality, it is often more efficient to ask for help than to search the entire space to find an object with an unknown location. We present a learning framework that enables an agent to actively ask for help in such embodied visual navigation tasks, where the feedback informs the agent of where the goal is in its view. To emulate the real-world scenario that a teacher may not always be present, we propose a training curriculum where feedback is not always available. We formulate an uncertainty measure of where the goal is and use empirical results to show that through this approach, the agent learns to ask for help effectively while remaining robust when feedback is not available.