Nov 2026· Journal of computing in civil engineering· 0 citations· 8 references
TL;DR
This framework combines simultaneous localization and mapping (SLAM), visual-language feature extraction, incremental semantic and instance label fusion, and spatial graph construction to enable a construction robot navigation framework that supports open-vocabulary language queries.
Abstract
Construction robots are increasingly capable of performing complex, labor-intensive tasks such as bricklaying, drilling, and autonomous material handling. Using real-time perception and environmental mapping, intelligent systems can operate effectively in unstructured and dynamic site conditions that traditionally demand human expertise. Recent progress in large language models and vision foundation models offers substantial opportunities to strengthen and extend the capability of creating high-level navigational maps for construction robots. Leveraging these advances, we introduce the zero-shot incremental vision–language maps framework, which is a three-dimensional (3D) modeling system that aims to generate semantically rich map representations of construction sites in a zero-shot manner. Our framework combines simultaneous localization and mapping (SLAM), visual-language feature extraction, incremental semantic and instance label fusion, and spatial graph construction to enable a construction robot navigation framework that supports open-vocabulary language queries. Evaluation is performed on the public ConSLAM dataset, and results show that the proposed framework is capable of building a rich 3D map of columns, signs, framework, and barriers in a construction environment.
Instance-Enriched Semantic Maps is proposed, a unified framework with three key contributions: instance-level two-and-a-half-dimensional rich information mapping, storage-efficient semantic representation that achieves approximately 96% reduction compared to three-dimensional scene-graph approaches while preserving sufficient spatial information for navigation, and robust query processing via LLM-based target selection.
J. Hong, Eunae Kang, Sanghyun Kim et al.· Engineering applications of...· 0 citations
This work presents SuperMap, a 4D spatio-temporal mapping framework for language-guided navigation that integrates high-frequency geometric SLAM with asynchronous open-vocabulary perception and releases the full system as open-source to provide the community with a deployable baseline for open-vocabulary spatio-temporal mapping.
Shibo Zhao, Guofei Chen, Honghao Zhu et al.· 1 citation
Lang2Graph is presented, an experimental framework for indoor topological graph inference from natural-language navigational instructions that isolates four governing factors: instruction structure, metadata clarity, prompting strategy, and model size and reasoning capability, and Reasoning-aligned open-source models of moderate scale (14B parameters) outperform larger proprietary models on the most challenging instruction categories.
Moamin Ibrahim, Yaqoob Ansari, Khaled A. Harras et al.· International Conference on...· 0 citations
Dense point cloud maps, as a typically used mapping representation, are difficult to deploy on resource-constrained robots because their memory consumption grows rapidly with scene scale. Although compact single-model representations reduce memory cost, their fixed geometric expressiveness is insufficient for structurally diverse environments. Existing multi-model methods improve representational flexibility, yet their feature extraction and model selection are often dominated by local geometry, which can cause overfitting and adhesion between objects. To address these issues, this paper presents M2-SMap, a memory-efficient semantic mapping framework based on hierarchical multi-model representation. First, a hierarchical geometric decomposition partitions RGB-D point clouds into compact Gaussian components. Then, a projection-guided semantic annotation mechanism assigns instance identities to each component. Subsequently, these annotations are incorporated into an object-aware Gaussian fusion strategy. Furthermore, a multi-scale feature extraction strategy separates large planar regions, semantic objects, and complex residual structures, which are respectively represented by bounded planes, object-level superquadrics, and GMM primitives. Experiments on three RGB-D sequences show that M2-SMap runs in real time at no less than 29.37 Hz while achieving the lowest primitive count, with an average reduction of 18.7% over the best baseline. It also reduces the mean per-frame number of measured inter-object adhesion cases from 2.808 to 0, demonstrating efficient and semantically consistent scene representation.
Prior-SG achieves state-of-the-art semantic region segmentation accuracy compared to recent baselines, robustly delineates distant functional boundaries in the absence of physical walls, and uniquely provides zero-shot ontological flexibility, enabling the robot to entirely restructure its spatial partitioning based on a given high-level task.
G. Tonetti, Laurent Kneip, Abel Gawel et al.· 0 citations
A modular mapping architecture is demonstrated that establishes 3D Semantic Scene Graphs (3DSSGs) as its foundational back-end, enabling the dense representation of extensive environments containing thousands of unique object instances and supporting open-vocabulary queries via CLIP features without requiring any additional post-processing steps.
F. Igelbrink, Lennart Niecksch, Martin G. ̈unther et al.· 0 citations