IGV-RRT: Prior-Real-Time Observation Fusion for Active Object Search in Changing Environments

TL;DR

This paper introduces IGV-RRT, a probabilistic planning framework that fuses prior scene knowledge with real-time semantic relevance to improve object search in changing indoor environments.

Contribution

It presents a novel dual-layer semantic mapping and a joint information gain and semantic evidence planner for active object search.

Findings

Higher search success rates in dynamic environments.

Improved efficiency over baseline methods.

Effective mitigation of object rearrangement impacts.

Abstract

Object Goal Navigation (ObjectNav) in temporally changing indoor environments is challenging because object relocation can invalidate historical scene knowledge. To address this issue, we propose a probabilistic planning framework that combines uncertainty-aware scene priors with online target relevance estimates derived from a Vision Language Model (VLM). The framework contains a dual-layer semantic mapping module and a real-time planner. The mapping module includes an Information Gain Map (IGM) built from a 3D scene graph (3DSG) during prior exploration to model object co-occurrence relations and provide global guidance on likely target regions. It also maintains a VLM score map (VLM-SM) that fuses confidence-weighted semantic observations into the map for local validation of the current scene. Based on these two cues, we develop a planner that jointly exploits information gain and semantic evidence for online decision making. The planner biases tree expansion toward semantically salient regions with high prior likelihood and strong online relevance (IGV-RRT), while preserving kinematic feasibility through gradient-based analysis. Simulation and real-world experiments demonstrate that the proposed method effectively mitigates the impact of object rearrangement, achieving higher search efficiency and success rates than representative baselines in complex indoor environments.