Short answer

Designers of educational tools and curricula for the construction industry should consider incorporating MLLM functionalities to create more immersive, adaptive, and effective training programs for human-robot collaboration.

Field: Innovation & Design
Source: ASCE OPEN Multidisciplinary Journal of Civil Engineering (2026)
Method: Narrative Literature Review
Evidence: Moderate effect

Multimodal Large Language Models (MLLMs) can significantly improve the learning of human-robot collaboration (HRC) in construction education by offering advanced capabilities for interpretation, communication, simulation, and personalized feedback. This innovation & design research insight is drawn from a 2026 study published in ASCE OPEN Multidisciplinary Journal of Civil Engineering. Using Narrative literature review, researchers explored how this design variable affects real-world outcomes. The key design takeaway: Designers of educational tools and curricula for the construction industry should consider incorporating MLLM functionalities to create more immersive, adaptive, and effective training programs for human-robot collaboration.

Study

Innovation & DesignNew This WeekModerate effect

Multimodal LLMs Enhance Human-Robot Collaboration Training in Construction

ASCE OPEN Multidisciplinary Journal of Civil Engineering · 2026

Key Findings

01MLLMs can interpret multimodal data, facilitating understanding of complex robotic operations.
02Natural language communication capabilities of MLLMs can improve interaction and instruction for HRC.
03Simulation-based learning powered by MLLMs can provide safe and repeatable training environments for HRC scenarios.
04MLLMs enable personalized learning paths and feedback, adapting to individual learner needs in HRC training.

Application

Design takeaway

How to apply

Develop or adopt educational software that uses MLLMs to provide interactive simulations of construction tasks involving robots, offering real-time feedback on user actions and communication.

Project actions

01When researching AI in design, consider how different types of AI can be applied to specific design challenges.
02Explore how multimodal AI can enhance user interaction and learning in technical fields.

Method & Evidence

AimHow can multimodal large language models be integrated into construction education to effectively teach human-robot collaboration skills?

MethodNarrative Literature Review

ProcedureThe researchers conducted a narrative review of literature from five domains (manufacturing, healthcare, robotics, construction, and education) to synthesize evidence on the capabilities of MLLMs and their potential application in HRC learning within construction education.

ContextConstruction Education and Human-Robot Collaboration

Variables

IV["Integration of Multimodal Large Language Models (MLLMs)"]

DV["Effectiveness of Human-Robot Collaboration (HRC) learning in construction education"]

CV["Existing construction education models","Challenges in current HRC training"]

Strengths & Limitations

Strengths

+Synthesizes research across multiple relevant domains.
+Identifies specific MLLM capabilities applicable to HRC learning.
+Provides a conceptual framework for future implementation.

Limitations

The practical implementation of MLLMs in educational settings may face challenges related to cost, accessibility, and the need for specialized technical expertise.

Reliability & validity

As a narrative review, the reliability and validity are dependent on the comprehensiveness of the literature search and the authors' synthesis. Empirical studies would be needed to establish the validity of the proposed applications.

Think critically

Beyond the identified benefits, what are the ethical considerations and potential biases that might arise from using MLLMs in educational settings for training in safety-critical fields like construction?

Design Principles

"Leverage AI-powered multimodal learning platforms to simulate and teach complex human-machine interactions in safety-critical industries."

As the construction industry increasingly relies on collaborative robotics, there's a growing need to train the workforce in effective HRC. MLLMs offer a novel approach to bridge the gap between current educational models and the practical skills required for safe and efficient human-robot interaction on construction sites.

What This Means for Your Design

This research suggests that using advanced AI tools that can understand text, images, and sounds (like MLLMs) can help students in construction learn how to work safely and effectively with robots.

How to use in your project

1.Reference this study when exploring the potential of AI tools to enhance practical skills training in your design project, particularly if it involves human-machine interaction or complex operational environments.

Add to My Project

Quick Cite

Paragraph starter

The integration of multimodal large language models (MLLMs) presents a significant opportunity to advance human-robot collaboration (HRC) training within construction education. As explored by Olukanni et al. (2026), MLLMs offer capabilities in multimodal data interpretation, natural language communication, simulation-based learning, and personalized feedback, which can collectively enhance the acquisition of HRC competencies. This suggests that future design projects focused on educational tools for the construction sector should consider leveraging MLLM functionalities to create more effective and adaptive learning environments for human-robot interaction.

Source

ASCE OPEN Multidisciplinary Journal of Civil Engineering

Multimodal Large Language Models in Construction Education for Learning Human–Robot Collaboration: A Narrative Review

journal · 2026

View source

Questions About This Research

What does the research say about multimodal llms enhance human-robot collaboration training in construction?: Designers of educational tools and curricula for the construction industry should consider incorporating MLLM functionalities to create more immersive, adaptive, and effective training programs for human-robot collaboration. Evidence: ASCE OPEN Multidisciplinary Journal of Civil Engineering (2026).
Why does "Multimodal LLMs Enhance Human-Robot Collaboration Training in Construction" matter for design?: As the construction industry increasingly relies on collaborative robotics, there's a growing need to train the workforce in effective HRC. MLLMs offer a novel approach to bridge the gap between current educational models and the practical skills required for safe and efficient human-robot interaction on construction sites.
How can designers apply this research?: Designers of educational tools and curricula for the construction industry should consider incorporating MLLM functionalities to create more immersive, adaptive, and effective training programs for human-robot collaboration.
What were the main findings?: MLLMs can interpret multimodal data, facilitating understanding of complex robotic operations.. Natural language communication capabilities of MLLMs can improve interaction and instruction for HRC.. Simulation-based learning powered by MLLMs can provide safe and repeatable training environments for HRC scenarios.. MLLMs enable personalized learning paths and feedback, adapting to individual learner needs in HRC training.
What research method was used?: Narrative Literature Review.
How strong is the evidence?: Evidence strength is rated Moderate effect, based on a 2026 journal from ASCE OPEN Multidisciplinary Journal of Civil Engineering.
What should I do differently in my next project?: Develop or adopt educational software that uses MLLMs to provide interactive simulations of construction tasks involving robots, offering real-time feedback on user actions and communication.
What are the limitations?: The review is conceptual and does not present empirical data on the direct implementation of MLLMs in construction HRC education; challenges in MLLM application were identified but require further investigation.