About

Arsalan Heydarian is an Associate Professor in the Department of Civil and Environmental Engineering at the University of Virginia, as well as a member of the UVA Link Lab. His research focuses on the user-centered design, construction, and operation of intelligent infrastructure, with the goal of enhancing sustainability, adaptability, and resilience. His work is organized into four primary research streams: intelligent built environments, mobility and infrastructure design, smart transportation, and data-driven mixed reality. Dr. Heydarian holds a Ph.D. in Civil Engineering and an M.Sc. in Systems Engineering from the University of Southern California, along with B.Sc. and M.Sc. degrees in Civil Engineering from Virginia Tech. He is also a co-founder of the Omni Reality and Cognition Lab (ORCL Lab), a facility that utilizes virtual and augmented reality technologies to study human behavior and responses to various infrastructure designs. His research interests include integrating human considerations within infrastructure systems, focusing on how buildings and vehicles can sense behaviors and collaborate with users to achieve personal goals, as well as designing transportation systems that enhance well-being, safety, and comfort.

Research topics

• Computer Science
• Engineering
• Artificial Intelligence
• Human–computer interaction
• Architectural engineering
• Business
• Psychology
• Mechanical engineering
• Environmental science
• Meteorology
• Geography
• Knowledge management
• Civil engineering
• Management science
• Construction engineering
• Engineering management
• Economics
• Telecommunications

Selected publications

• UAV-Based Infrastructure Inspections: A Literature Review and Proposed Framework for AEC+FM

  Open MIND · 2026-01-16

  preprintSenior author

  Unmanned Aerial Vehicles (UAVs) are transforming infrastructure inspections in the Architecture, Engineering, Construction, and Facility Management (AEC+FM) domain. By synthesizing insights from over 150 studies, this review paper highlights UAV-based methodologies for data acquisition, photogrammetric modeling, defect detection, and decision-making support. Key innovations include path optimization, thermal integration, and advanced machine learning (ML) models such as YOLO and Faster R-CNN for anomaly detection. UAVs have demonstrated value in structural health monitoring (SHM), disaster response, urban infrastructure management, energy efficiency evaluations, and cultural heritage preservation. Despite these advancements, challenges in real-time processing, multimodal data fusion, and generalizability remain. A proposed workflow framework, informed by literature and a case study, integrates RGB imagery, LiDAR, and thermal sensing with transformer-based architectures to improve accuracy and reliability in detecting structural defects, thermal anomalies, and geometric inconsistencies. The proposed framework ensures precise and actionable insights by fusing multimodal data and dynamically adapting path planning for complex environments, presented as a comprehensive step-by-step guide to address these challenges effectively. This paper concludes with future research directions emphasizing lightweight AI models, adaptive flight planning, synthetic datasets, and richer modality fusion to streamline modern infrastructure inspections.

  DOI

• UAV-Based Infrastructure Inspections: A Literature Review and Proposed Framework for AEC+FM

  ArXiv.org · 2026-01-16

  articleOpen accessSenior author

  Unmanned Aerial Vehicles (UAVs) are transforming infrastructure inspections in the Architecture, Engineering, Construction, and Facility Management (AEC+FM) domain. By synthesizing insights from over 150 studies, this review paper highlights UAV-based methodologies for data acquisition, photogrammetric modeling, defect detection, and decision-making support. Key innovations include path optimization, thermal integration, and advanced machine learning (ML) models such as YOLO and Faster R-CNN for anomaly detection. UAVs have demonstrated value in structural health monitoring (SHM), disaster response, urban infrastructure management, energy efficiency evaluations, and cultural heritage preservation. Despite these advancements, challenges in real-time processing, multimodal data fusion, and generalizability remain. A proposed workflow framework, informed by literature and a case study, integrates RGB imagery, LiDAR, and thermal sensing with transformer-based architectures to improve accuracy and reliability in detecting structural defects, thermal anomalies, and geometric inconsistencies. The proposed framework ensures precise and actionable insights by fusing multimodal data and dynamically adapting path planning for complex environments, presented as a comprehensive step-by-step guide to address these challenges effectively. This paper concludes with future research directions emphasizing lightweight AI models, adaptive flight planning, synthetic datasets, and richer modality fusion to streamline modern infrastructure inspections.

  PublisherOA PDF

• Human-centered energy modeling: integrating occupant behavior in simulation workflows

  Energy and Buildings · 2026-01-08

  article
  PublisherDOI

• Real-Time Roadway Obstacle Detection for Electric Scooters Using Deep Learning and Multi-Sensor Fusion

  ArXiv.org · 2025-04-04 · 1 citations

  preprintOpen accessSenior author

  The increasing adoption of electric scooters (e-scooters) in urban areas has coincided with a rise in traffic accidents and injuries, largely due to their small wheels, lack of suspension, and sensitivity to uneven surfaces. While deep learning-based object detection has been widely used to improve automobile safety, its application for e-scooter obstacle detection remains unexplored. This study introduces a novel ground obstacle detection system for e-scooters, integrating an RGB camera, and a depth camera to enhance real-time road hazard detection. Additionally, the Inertial Measurement Unit (IMU) measures linear vertical acceleration to identify surface vibrations, guiding the selection of six obstacle categories: tree branches, manhole covers, potholes, pine cones, non-directional cracks, and truncated domes. All sensors, including the RGB camera, depth camera, and IMU, are integrated within the Intel RealSense Camera D435i. A deep learning model powered by YOLO detects road hazards and utilizes depth data to estimate obstacle proximity. Evaluated on the seven hours of naturalistic riding dataset, the system achieves a high mean average precision (mAP) of 0.827 and demonstrates excellent real-time performance. This approach provides an effective solution to enhance e-scooter safety through advanced computer vision and data fusion. The dataset is accessible at https://zenodo.org/records/14583718, and the project code is hosted on https://github.com/Zeyang-Zheng/Real-Time-Roadway-Obstacle-Detection-for-Electric-Scooters.

  PublisherOA PDFDOI

• Multimodal Foundation Models for Zero-Shot Water Stress Forecasting in Precision Agriculture

  2025-12-03

  articleSenior author

  Foundation models for time-series forecasting offer powerful new capabilities, yet adapting them to specialized domains without costly retraining remains a critical challenge. This paper addresses this challenge by demonstrating that for high-frequency multimodal data, a zero-shot inference approach can significantly outperform not only fine-tuned variants but also traditional deep learning baselines. We introduce a novel framework that uses the Segment Anything Model (SAM) for visual plant phenotyping (e.g., RGB values, mask area, and plant dimensions) and the Lag-Llama foundation model for water-stress forecasting. Validated on a dataset of over 43,000 images and corresponding minute-level IoT sensor data, our zero-shot model achieves a Mean Squared Error (MSE) of 0.0062. This represents a 58.1% lower error than a unimodal variant (MSE 0.0148) and a 99.95% MSE reduction relative to a CNN+LSTM baseline (11.91 → 0.0062). These findings highlight a robust and computationally efficient pathway for deploying foundation models in complex, real-world systems. The methodologies and open-source contributions presented advance the application of machine learning in precision agriculture and provide a valuable framework for multimodal, zero-shot time-series analysis.

  PublisherDOI

• A Vision-Language Model Agent for building code compliance

  2025-11-11

  articleOpen accessSenior author

  Traditional methods for ensuring building code compliance often demand substantial time and resources and are prone to human error, leading to inconsistent evaluations of critical residential systems. Such inconsistencies can result in overlooked safety hazards and costly future repairs. To address these challenges, this paper introduces an innovative Vision-Language Model (VLM) agent specifically designed for building code compliance. The proposed agent combines advanced reasoning and action capabilities with specialized tools. It leverages a knowledge base comprising key building codes, including the International Residential Code (IRC) and the International Plumbing Code (IPC), and employs Retrieval-Augmented Generation (RAG) to identify relevant standards tailored to specific compliance requirements. An interactive interface enables users to submit both images and text, which the agent systematically analyzes. The VLM agent detects critical components, such as P-traps, and retrieves corresponding building code references. The system then generates a comprehensive report summarizing identified issues, assessing their severity, and citing relevant code sections. We use four distinct building components from real home inspection reports to evaluate the system's performance. The VLM agent achieves an average 96.25% similarity with the human-created inspection report. This research demonstrates a practical application of VLM agents, significantly enhancing the accuracy, accessibility, and reliability of building code compliance processes.

  PublisherOA PDFDOI

• Multimodal Data Integration for Sustainable Indoor Gardening: Tracking Anyplant with Time Series Foundation Model

  ArXiv.org · 2025-03-27

  preprintOpen accessSenior author

  Indoor gardening within sustainable buildings offers a transformative solution to urban food security and environmental sustainability. By 2030, urban farming, including Controlled Environment Agriculture (CEA) and vertical farming, is expected to grow at a compound annual growth rate (CAGR) of 13.2% from 2024 to 2030, according to market reports. This growth is fueled by advancements in Internet of Things (IoT) technologies, sustainable innovations such as smart growing systems, and the rising interest in green interior design. This paper presents a novel framework that integrates computer vision, machine learning (ML), and environmental sensing for the automated monitoring of plant health and growth. Unlike previous approaches, this framework combines RGB imagery, plant phenotyping data, and environmental factors such as temperature and humidity, to predict plant water stress in a controlled growth environment. The system utilizes high-resolution cameras to extract phenotypic features, such as RGB, plant area, height, and width while employing the Lag-Llama time series model to analyze and predict water stress. Experimental results demonstrate that integrating RGB, size ratios, and environmental data significantly enhances predictive accuracy, with the Fine-tuned model achieving the lowest errors (MSE = 0.420777, MAE = 0.595428) and reduced uncertainty. These findings highlight the potential of multimodal data and intelligent systems to automate plant care, optimize resource consumption, and align indoor gardening with sustainable building management practices, paving the way for resilient, green urban spaces.

  PublisherOA PDFDOI

• A Sequential and Dynamic Analysis of Pedestrian Street Crossing Decisions in Day and Night Scenarios: A Case Study in Charlottesville, Virginia

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access
  PublisherDOI

• Detecting Plant Voc Traces Using Indoor Air Quality Sensors

  SSRN Electronic Journal · 2025-01-01 · 2 citations

  preprintOpen accessSenior author
  PublisherDOI

• Performance Evaluation of Real-Time Object Detection for Electric Scooters

  2025-12-11

  articleCorresponding

  Electric scooters (e-scooters) have rapidly emerged as a popular mode of transportation in urban areas, yet they pose significant safety challenges. In the United States, the rise of e-scooters has been marked by a concerning increase in related injuries and fatalities. Recently, while deep-learning object detection holds paramount significance in autonomous vehicles to avoid potential collisions, its application in the context of e-scooters remains relatively unexplored. This paper addresses this gap by assessing the effectiveness and efficiency of cutting-edge object detectors designed for e-scooters. To achieve this, the first comprehensive benchmark involving 22 state-of-the-art YOLO object detectors, including five versions (YOLOv3, YOLOv5, YOLOv6, YOLOv7, and YOLOv8), has been established for real-time traffic object detection using a self-collected data set featuring e-scooters. The detection accuracy, measured in terms of [email protected], ranges from 27.4% (YOLOv7-E6E) to 86.8% (YOLOv5s). All YOLO models, particularly YOLOv3-tiny, have displayed promising potential for real-time object detection in the context of e-scooters. Both the traffic scene data set and software program codes for model benchmarking in this study are publicly available, which will not only improve e-scooter safety with advanced object detection but also lay the groundwork for tailored solutions, promising a safer and more sustainable urban micromobility landscape.

  PublisherDOI

Recent grants

• CRI:II-New: The Living Link Lab: Infrastructure for Enhancing Occupant Experience and Building Operations

  NSF · $755k · 2018–2022

Frequent coauthors

• Arash Tavakoli

  Stanford University

  67 shared

• Xiang Guo

  University of Virginia

  39 shared

• Vahid Balali

  34 shared

• Erin Robartes

  Virginia Transportation Research Council

  23 shared

• Austin Angulo

  University at Buffalo, State University of New York

  22 shared

• Mahsa Pahlavikhah Varnosfaderani

  21 shared

• T. Donna Chen

  20 shared

• Farrokh Jazizadeh

  Virginia Tech

  17 shared

Labs

• Link LabPI

Education

• PhD, Civil and Environmental Engineering

  University of Southern California

  2017