Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation
This addresses efficiency in navigation tasks for AI agents, though it is incremental as it builds on existing navigation frameworks with a novel help-asking mechanism.
The paper tackles the problem of embodied visual navigation by enabling agents to actively ask for help when uncertain about goal locations, resulting in effective help-seeking behavior and robustness to unavailable feedback.
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.