cs.RONov 7, 2026

HSGNav: Hypothesis Scene Graphs for Multi-Scale Lifelong Navigation under Object Relocation

Authors: Kaiyao Liao, Qingfeng Li, Chen Chen, Qing Sun, Ningbo Gu, Xiaoze Wu, Haochen Zhao, Ying Li, 

Organizations: Beihang University, Beijing, China · Hangzhou Innovation Institute, Beihang University, Hangzhou, China

Abstract

In real homes, assistive robots must repeatedly locate targets from large furniture to tiny tabletop items, as people move objects between household surfaces. Uniformly instantiating detections at different scales as 3D objects can be brittle for small on-surface items; without explicit object-state validation, stale entries may persist after scene changes. Our key insight is to separate persistent 3D furniture entities from revisable surface-object hypotheses, retaining their visual evidence without requiring independent object geometry. We formalize this design as the Hypothesis Scene Graph (HSG), which preserves small-object evidence and supports local revision without rebuilding the stable entity topology. Building on HSG, HSGNav uses this separation for multi-scale lifelong navigation: retrieval selects entity or hypothesis evidence according to target scale, exploration acquires additional surface observations, and verification confirms target presence or invalidates contradicted hypothesis records. Because existing lifelong benchmarks such as GOAT-Bench rarely require mid-episode memory invalidation or multi-scale search, we introduce FAROS-Bench (Find And Re-find Objects across Scales) for mid-episode relocation of surface objects and multi-scale find goals. Experiments show that HSGNav performs competitively on GOAT-Bench while substantially outperforming prior methods on FAROS-Bench.

Figures & tables

Explore similar work

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

    Oct 7, 2026Jiagan Huang, Zikun Zhou, Zijian Ni +4Visual NavigationObject-Goal Navigation

  2. OmniNav: Robust Long-Horizon Target Navigation in Dynamic Environments

    Sep 8, 2026Yujie Tang, Meiling Wang, Jinhao Jiang +4Robot NavigationObject-Goal Navigation

  3. Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation

    Apr 5, 2026Peixin Chen, Guoxi Zhang, Jianwei Ma +1Embodied NavigationGraph-Based Agent Memory