Lifelong small-object navigation in changing object layouts: a benchmark and method

2026-10-07

AI Summary

This study addresses the perceptual and memory-updating challenges faced by domestic robots navigating toward small objects in dynamically changing environments, where weak visual features, frequent occlusions, and unknown object locations hinder reliable operation. To overcome these issues, this work proposes the IVAM-Nav framework, which enhances perception through multi-view active observation and introduces a viewpoint-anchored memory mechanism to support relational memory reuse and re-verification, effectively resolving the cold-start problem in scenarios without prior environment scanning. Furthermore, it presents LiSoNav-Eval, the first lifelong small-object navigation benchmark tailored for layout-changing environments. Experimental results demonstrate that the proposed method significantly outperforms existing baselines while revealing how object size, environment scale, and travel distance systematically influence navigation performance.

Abstract

Household robots need to continually navigate to different objects in the same environment, many of which are small and portable, such as tools and toys. Their small visual footprint and frequent occlusion make reliable observation difficult, and they may be moved by people without the robot observing the changes. We formulate this challenging task as Lifelong Small-object Navigation in Changing Object Layouts (LiSoNav-COL). Agents must seek suitable viewpoints for reliable observation, accumulate and reuse scene knowledge to efficiently locate subsequent targets, and update outdated memory after object relocation. To eliminate the need for prior scene scanning, we also require agents to start navigation with empty scene memory. Although practical, this task still lacks benchmarks designed around its defining assumptions. To bridge this gap, we introduce LiSoNav-Eval, a dedicated benchmark spanning 28 indoor scenes with 45 small-object categories. Its lifelong navigation sequences include both unchanged and relocated targets to evaluate memory reuse and adaptation to object relocation. To address this challenging task, we propose a navigation method based on multi-view Inspection with Viewpoint-Anchored Memory, dubbed IVAM-Nav. IVAM-Nav actively observes supporting surfaces from complementary viewpoints for reliable small-object perception and anchors the resulting memory to their observation viewpoints, supporting relational memory reuse and revalidation under similar viewing conditions. Extensive experiments on LiSoNav-Eval demonstrate favorable performance of IVAM-Nav against representative methods. Benchmark analyses also show that smaller objects, larger environments, and longer relocation distances pose greater challenges. The dataset and code are available here.

Problem

• lifelong navigation
• small-object detection
• object relocation
• household robots
• benchmark

Innovation

• Lifelong navigation
• Small-object perception
• Viewpoint-anchored memory
• Multi-view inspection
• Object relocation