OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation

TL;DR

OVAL is a new lifelong open-vocabulary memory framework that improves long-term object navigation by structured memory management and a novel exploration strategy, enabling efficient navigation in semantically open tasks.

Contribution

The paper introduces OVAL, a novel lifelong memory framework with memory descriptors and a probability-based exploration strategy for improved object navigation.

Findings

Demonstrates efficiency and robustness in experiments.

Enhances lifelong exploration with multi-value frontier scoring.

Enables precise long-term navigation in open-vocabulary settings.

Abstract

Object Goal Navigation (ObjectNav) refers to an agent navigating to an object in an unseen environment, which is an ability often required in the accomplishment of complex tasks. While existing methods demonstrate proficiency in isolated single object navigation, their limitations emerge in the restricted applicability of lifelong memory representations, which ultimately hinders effective navigation toward continual targets over extended periods. To address this problem, we propose OVAL, a novel lifelong open-vocabulary memory framework, which enables efficient and precise execution of long-term navigation in semantically open tasks. Within this framework, we introduce memory descriptors to facilitate structured management of the memory model. Additionally, we propose a novel probability-based exploration strategy, utilizing a multi-value frontier scoring to enhance lifelong exploration efficiency. Extensive experiments demonstrate the efficiency and robustness of the proposed system.