Semantic Semi-Incremental Data-Association-Free Object SLAM

2026-07-25

AI Summary

This work addresses the degradation in pose and map estimation accuracy in SLAM caused by erroneous data association by proposing a semantic SLAM framework that eliminates the need for explicit data association. The approach formulates a probabilistic graphical model to jointly optimize robot poses, landmark positions, semantic labels, and implicit data associations, integrating odometry, positional measurements, and semantic observations—including category labels and features from vision foundation models. Innovatively, it co-models semantic inference and data association within a semi-incremental optimization strategy and provides both theoretical justification and practical heuristics for estimating the number of landmarks. Experimental results demonstrate consistent superiority over strong baselines on both synthetic and real-world datasets, achieving high accuracy in localization and mapping while remaining compatible with diverse semantic inputs.

Abstract

Data association between landmark measurements and landmark variables has long been a central challenge in SLAM, as estimation accuracy depends critically on associating measurements with the correct landmark variables. Recent advances in deep learning have created new opportunities for the problem; data association can now leverage not only positional measurements but also semantic information about object landmarks, such as class labels from neural object detectors and feature vectors from visual foundation models. In this paper, we present a generalized data-association-free SLAM framework that jointly estimates data associations, robot poses, landmark positions, and landmark semantics from odometry, and positional and semantic measurements of landmarks. The proposed framework (i) creates a synergy between data association and landmark semantics estimation; (ii) adopts a semi-incremental estimation scheme for improved accuracy and computational efficiency; and (iii) provides a principled justification, guidelines, and heuristics for landmark-number estimation, improving the interpretability and practical usability of the framework. The proposed framework and algorithms are evaluated on synthetic and real-world datasets with two types of semantic information, class labels and real-valued feature vectors, and demonstrate superior performance compared to strong baselines.

Problem

• data association
• semantic SLAM
• object landmarks
• simultaneous localization and mapping
• landmark semantics

Innovation

• data-association-free
• semantic SLAM
• semi-incremental estimation
• landmark semantics
• object-based SLAM