Explore and Explain: Self-supervised Navigation and Recounting

TL;DR

This paper introduces a new embodied AI setting where agents explore unknown environments, generate natural language descriptions of their observations, and make decisions based on integrated self-supervised exploration and captioning models.

Contribution

It presents a novel self-supervised exploration module combined with an attentive captioning model for explanation in embodied AI navigation tasks.

Findings

Effective exploration and explanation in photorealistic environments

Interaction between navigation and explanation improves agent performance

Different explanation policies impact the quality of descriptions

Abstract

Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment while recounting what it sees during the path. In this context, the agent needs to navigate the environment driven by an exploration goal, select proper moments for description, and output natural language descriptions of relevant objects and scenes. Our model integrates a novel self-supervised exploration module with penalty, and a fully-attentive captioning model for explanation. Also, we investigate different policies for selecting proper moments for explanation, driven by information coming from both the environment and the navigation. Experiments are conducted on photorealistic environments from the Matterport3D dataset and investigate the navigation and explanation capabilities of the agent as well as the role of their interactions.