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

2026-04-14

AI Summary

This work addresses the limitations of existing object navigation methods in lifelong, open-vocabulary semantic environments, where inadequate lifelong memory representations hinder efficient adaptation to sequentially encountered novel targets. To overcome this challenge, we propose OVAL, a framework that introduces the first open-vocabulary memory model tailored for lifelong navigation. OVAL enables scalable management of semantic memory through structured memory descriptors and incorporates a probabilistic multi-value frontier exploration strategy to enhance long-term exploration efficiency. Experimental results demonstrate that OVAL significantly improves success rates and exploration robustness in open semantic settings, effectively overcoming the bottlenecks of conventional approaches in semantic generalization and long-term memory retention.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Life-Long and Continual Learning
• Computer Vision: Learning & Optimization for CV

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Object Goal Navigation
• lifelong memory
• open-vocabulary
• continual targets
• navigation efficiency

Innovation

• open-vocabulary
• lifelong memory
• memory descriptors
• probability-based exploration
• multi-value frontier scoring