DiCE Research Lab

Data‑informed Construction Engineering

We advance Construction and Civil Engineering through fundamental and use-inspired interdisciplinary research in robotics, automation, and artificial intelligence to improve the design, construction, and management of civil infrastructure.

Research Areas

Robotics · Artificial Intelligence · Construction Automation · Adaptive Control · Worker-Robot Interaction

Robotics

Developing mobile and field robotic systems for construction and infrastructure projects that can perceive, navigate, and operate safely in complex environments.

Artificial Intelligence

Using computer vision, machine learning, and data analytics to interpret construction data, enhance decision-making, and enable intelligent automation.

Construction Automation

Designing automated systems that improve productivity, safety, and quality through advanced sensing, digital modeling, and autonomous control.

Adaptive Control

Creating control algorithms that allow robotic and automated systems to respond effectively to changes in environment, load, or task conditions.

Worker-Robot Interaction

Studying and developing methods that enable intuitive and safe collaboration between human workers and robots on dynamic construction sites.

Featured Projects

Current research projects by DiCE Lab

Contextual information representation strategies

Formulation of task dependent and closed form representations to fuse contextual information such as natural language or safety constraints with classical methods that guarantee optimality and interpretability.

Intelligent robot navigation in dynamic construction sites

Development of adaptive navigation frameworks integrating BIM data, natural language understanding, and multi-heuristic path planning to enable context-aware, obstacle-responsive autonomy for safer and more reliable construction robotics.

Latest Publications

S. Ergan, M. Sujon, F. Dai, E. Du, R. Akhavian, and A. Behzadan, “To-Practice Drivers and Barriers: Visualization, Information Modeling, and Simulation Technologies in AEC/FM,” Journal of Computing in Civil Engineering, vol. 40, no. 1, 04025128, 2026.
M. Amani and R. Akhavian, “Safe and trustworthy robot pathfinding with BIM, MHA*, and NLP,” Construction Robotics, vol. 9, no. 2, p. 18, 2025.
R. Akhavian, M. Amani, J. Mootz, R. Ashe, and B. Beheshti, “Building Information Models to Robot-Ready Site Digital Twins (BIM2RDT): An Agentic AI Safety-First Framework,” arXiv preprint arXiv:2509.20705, 2025.
M. Amani and R. Akhavian, “Digital Twin-Guided Robot Path Planning: A Beta-Bernoulli Fusion with Large Language Model as a Sensor,” arXiv preprint arXiv:2509.20709, 2025.
J. Mootz and R. Akhavian, “Advancing Accessible Hand-Arm Vibration Safety Monitoring: ISO-Compliance with Wearable Sensors and Transfer Functions,” arXiv preprint arXiv:2509.16536, 2025.
R. Ashe, M. Amani, C. Sommerfield, and R. Akhavian, “A Modular Quadruped Control and Sensor Integration Framework with a Case Study in Worker Activity Recognition,” American Society of Civil Engineers, 2025
J. Mootz, M. Amani, and R. Akhavian, “Safer Online Replanning for Construction Robots via NLP-Informed Potential Fields and BIM Semantics,” IEEE International Conference on Robotics and Automation (ICRA), 2025
M. Amani and R. Akhavian, “Bayesian BIM-Guided Construction Robot Navigation with NLP Safety Prompts in Dynamic Environments,” arXiv preprint arXiv:2501.17437, 2025
M. Amani and R. Akhavian, “Intelligent ergonomic optimization in bimanual worker-robot interaction: A Reinforcement Learning approach,” Automation in Construction 168: 105741, 2024
M. Amani and R. Akhavian, “Adaptive Robot Perception in Construction Environments using 4D BIM,” arXiv preprint arXiv:2409.13837, 2024