Robust Graph Matching through Semantic Relationship Generation for SLAM

TL;DR

This paper introduces a semantic-enhanced graph matching method for SLAM that leverages object relations to improve localization accuracy and efficiency in symmetric environments.

Contribution

It explicitly models semantic relations between objects and structural elements to reduce ambiguity in graph matching for SLAM.

Findings

Semantic relations reduce candidate matches significantly.

Method improves computational efficiency in symmetric environments.

Faster convergence achieved in synthetic and simulated tests.

Abstract

Graph-based representations such as Scene Graphs enable localization in structured indoor environments by matching a locally observed graph, constructed from sensor data, to a prior map. This process is particularly challenging in environments with repetitive or symmetric layouts, where structural cues alone are often insufficient to resolve ambiguities. We propose a semantic-enhanced graph matching approach that explicitly models relations between detected objects and structural elements, such as rooms and wall planes. Objects are detected from RGB-D data and integrated into the graph, and their relations to structural elements are exploited to filter candidate correspondences prior to geometric verification, significantly reducing ambiguity and search complexity. The proposed method is integrated within the iS-Graphs framework and evaluated in synthetic and simulated environments. Results show that semantic relations significantly reduce the number of candidate matches, improve computational efficiency, and enable faster convergence, particularly in symmetric scenarios where purely geometric approaches fail.