Dynamic and continuously evolving environments present significant challenges for robotic mapping and scene understanding, particularly on construction sites where moving agents, temporary obstacles, and persistent structural changes coexist. While dynamic and long-term SLAM methods can detect motion and environmental changes, their outputs are predominantly metric representations that provide limited structure for higher-level spatial and temporal reasoning. This paper presents a LiDAR-based real-time temporal construction scene graph (T-ConSG) that jointly represents free-space regions, static objects, dynamic objects, and environmental events with spatial-relational and event-participation edges. The proposed framework incrementally constructs the graph from LiDAR-derived geometric evidence, maintaining persistent free-space and static-object information while tracking dynamic objects. Changes in accumulated spatial evidence are further represented as explicit installation and removal events, allowing the graph to capture both transient dynamics and persistent environmental evolution. We demonstrate the proposed representation through three complementary application studies: dynamics-aware navigation in a bricklaying testbed, construction progress monitoring on the ConSLAM dataset, and online change detection in a simulated construction environment. The results demonstrate that the proposed T-ConSG provides a unified representation for organizing spatial and temporal information and supports robotic reasoning across environments containing both short-term dynamics and persistent changes.
Figures & tables
Fig. 1: Overall workflow.
Fig. 2: Dynamic-object tracking and association.
Fig. 3: Temporal construction scene graph.
Fig. 4: Bricklaying testbed. (a) Layout. (b) Robot with LiDAR.
Planner
Path len.
Path irr.
CPD
Min. TTC
(m)
(rad/m)
(m)
(s)
Original
83.13 ± 8.12
8.49 ± 1.07
2.60 ± 0.10
4.76 ± 1.77
SFM
88.48 ± 8.81
10.64 ± 1.26
2.62 ± 0.10
5.11 ± 1.93
TABLE I: Evaluation results on the bricklaying test. Values are means ± standard deviations across 10 trials.
Fig. 5: Free-space and static-object regions, together with estimated removal and installation regions across ConSLAM sequences: (a) Sequence 2. (b) Sequence 3. (c) Sequence 4. (d) Sequence 5.
Seq.
Free
Recall
Static
Recall
Installed
Removed
( m2 )
(%)
( m2 )
(%)
( m2 )
( m2 )
2
5646.20
92.39
540.24
92.89
-
-
3
7439.64
92.81
704.68
82.66
157.40
100.28
4
5786.56
89.82
740.24
93.51
140.52
105.70
5
6249.84
90.86
854.64
76.77
233.48
173.60
TABLE II: Free-space and static-object areas and recall, with estimated inter-sequence installation and removal areas across ConSLAM sequences.
Fig. 6: Simulated construction site. (a) Layout. (b) Unity view.
Fig. 7: Free space and static object maps along the robot trajectory in trial 1. The free space, static objects, dynamic objects, and spatial-relational edges related to A and B are visualized before and after the structural changes, including the time when the changes occur. (a) Initial exploration. (b) Structural changes occur. (c) Installation detected. (d) Removal detected.
In indoor environments, object positions frequently change due to human activities or embodied-agent interactions, causing previously constructed scene graphs to become inconsistent with the current scene. To address this issue, we propose DSG, a dynamic 3D scene graph construction framework that detects object changes and performs spatial relationship reasoning. First, we construct a semantic-aware 3D Gaussian scene representation and develop a dual-view rendering-based object change detection method to enable reliable scene graph node updates. Second, we propose a spatial relationship reasoning method that incorporates multi-granularity visual context, enabling a large language model to identify a richer set of interobject spatial relationships. Furthermore, we introduce DynTHOR, a dynamic indoor scene graph benchmark built on the AI2-THOR simulation platform for evaluating scene graph construction in dynamic environments. Extensive experiments on Dyn-THOR, 3RScan, and real-world scenes demonstrate that DSG consistently outperforms existing methods in both object node construction and spatial relationship reasoning, significantly improving the accuracy of dynamic scene graph construction.
Ming Liao, Chao Ye, Jianing Fei +1
Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150001, China
Robust dynamic object detection and tracking are essential for enabling robots to operate safely and effectively alongside humans in complex environments such as construction sites. While LiDAR-based SLAM and occupancy grid methods offer viable solutions for detecting and tracking motion, many state-of-the-art 3D vision approaches rely heavily on pre-trained neural networks and require additional post-processing to identify moving objects. Sensor fusion techniques, combining the precision of LiDAR with the semantic richness of RGB imagery, offer a promising alternative. In this work, we present a novel framework that enhances a quadruped robot equipped with a LiDAR sensor and an upward-facing fisheye camera for real-time dynamic object detection and tracking. After identifying moving objects within a registered point cloud, our method assigns semantic labels by projecting 3D coordinates onto a 2D cylindrical panorama, aligning with real-time image-based detections for observation update of the Kalman filter. The proposed system demonstrates high precision, simplicity, and robustness, particularly in handling objects transitioning between dynamic and static states, thus it is well-suited for deployment in real-world construction environments.
Yilong Chen, Huili Huang, Yong K. Cho
Georgia Institute of Technology, Atlanta, GA 30332, USA
We propose SEAM, a LiDAR-based lifelong mapping framework. Instead of relying on a single anchor spanning the entire session, SEAM generates evidence based on a trajectory optimized with submap-level anchors, and performs dynamic object removal and change detection. Through submap-level reprojection, the generated evidence remains usable even if the trajectory is subsequently modified by a new session, eliminating the need to recompute the entire process from scratch. SEAM suppresses geometrically unreliable inter-session loop edges using a DOP-based confidence measure. Suppressing unreliable loop edges prevents alignment errors. SEAM also uses a directional voxel-wise evidence model. The model accounts for occupancy patterns that vary with ray direction. Direction-aware evidence separates dynamic objects from environmental changes more precisely. Experiments on a real construction-site dataset and a long-term multi-session dataset show that SEAM achieves higher accuracy and faster processing than existing methods.
Kyuwon Kim
HMG Construction R&D Division, Hyundai Engineering & Construction, Seoul, Republic of Korea