Automation in Construction

6 papers10 directions
Automation in Construction is a research venue focused on the integration of information technologies, robotics, and artificial intelligence within the built environment. It serves as a platform for applying computational methods to civil engineering and construction management challenges. Recent research published at this venue highlights a significant shift toward deep learning applications, particularly in computer vision and spatial data processing. Key contributors include researchers such as Jifeng Shen, Xin Zuo, Yongwei Shan, and Brian Sheil, with active contributions documented between 2019 and 2026. The venue’s technical scope encompasses a variety of machine learning tasks tailored to infrastructure and site operations. Published studies include the use of diffusion models and prompted segmentation for depth map restoration from sparse point clouds, as well as transformer-based architectures for the semantic segmentation of recycling materials. Other research focuses on structural health monitoring, such as crack segmentation using topology-aware models and sub-class classification of defects in sewer inspection videos. Additionally, the venue features work on anomalous event detection and tracking for specialized systems like tunnel ground prediction. In the broader machine learning community, Automation in Construction functions as a specialized outlet for applied AI research. It bridges the gap between general-purpose algorithmic development and the practical constraints of the construction industry. By hosting studies on automated tracking, material understanding, and predictive maintenance, the venue facilitates the adaptation of state-of-the-art AI techniques to handle the complex, real-world data environments inherent to large-scale infrastructure projects.

Papers by Year

2026 1
2024 2
2020 1
2019 1
2018 1

Top Research Directions

Research directions most represented by papers from this venue.

Locality Preserving Serialization for Vision Sequence Models 1
Zero-Shot Inverse Problem Solving with Diffusion Models 1
Integrating Geometry and Appearance to Resolve Spatial Ambiguity 1
Linear Time Sequence Modeling with Selective State Space Models 1
Overcoming Local Receptive Field Constraints in Visual Models 1
Weighted Model Ensembling 1
Model Ensembling for Robustness and Generalization 1
Encoder-Decoder Networks with Skip Connections 1
Overcoming the Iterative Denoising Bottleneck 1
Efficient Vision Transformers for Edge Deployment 1

Top Authors

AuthorPapers
Jifeng Shen2
Anthony G Cohn1
Edgar Lobaton1
Guangming Wang1
Ting Cai1
Yin Li1

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Papers

TitleYear
Zero-shot depth map restoration from sparse infrastructure point clouds using diffusion models and prompted segmentation2026
Topology-aware mamba for crack segmentation in structures2024
Transformer-based automated segmentation of recycling materials for semantic understanding in construction2024
Classifying cracks at sub-class level in closed circuit television sewer inspection videos2020
An anomalous event detection and tracking method for a tunnel look-ahead ground prediction system2019
Vision-based integrated mobile robotic system for real-time applications in construction2018