Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation

TL;DR

This paper introduces a novel memory system for vision-and-language navigation agents that combines imagination and episodic memory, significantly improving their ability to navigate unseen environments by imagining future scenes.

Contribution

The paper proposes a reality-imagination hybrid memory architecture and pre-training tasks that enable agents to imagine future scenes, enhancing navigation performance.

Findings

Achieved state-of-the-art SPL performance in VLN tasks.

Developed a hybrid memory system inspired by human episodic memory.

Enabled agents to generate high-fidelity imagined scenes.

Abstract

Humans navigate unfamiliar environments using episodic simulation and episodic memory, which facilitate a deeper understanding of the complex relationships between environments and objects. Developing an imaginative memory system inspired by human mechanisms can enhance the navigation performance of embodied agents in unseen environments. However, existing Vision-and-Language Navigation (VLN) agents lack a memory mechanism of this kind. To address this, we propose a novel architecture that equips agents with a reality-imagination hybrid memory system. This system enables agents to maintain and expand their memory through both imaginative mechanisms and navigation actions. Additionally, we design tailored pre-training tasks to develop the agent's imaginative capabilities. Our agent can imagine high-fidelity RGB images for future scenes, achieving state-of-the-art result in Success rate weighted by Path Length (SPL).