# Human-Robot Collaboration in Construction: Assessing Cognitive Factors for Construction Workers Using Virtual Reality-Wearable Devices-Data Analytics Integrated Approach

> **NIH ALLCDC R21** · MISSISSIPPI STATE UNIVERSITY · 2024 · $129,299

## Abstract

The emerging Human-Robot Collaboration (HRC) is reshaping the traditional construction processes, introducing new
uncertainties and complexities, and leading to unforeseen interactions and safety concerns. In traditional construction
contexts, research into cognitive risk factors such as mental fatigue, stress, and attention has been a focal point for ensuring
worker safety. However, as we shift into the realm of HRC in construction where novel challenges and safety and health
risks surrounding the construction workforce have emerged, there's a noticeable gap in understanding and explaining how
these cognitive risk factors manifest and interplay. The existing literature on human cognitive risk factors in HRC is very
limited, overlooking the complexities and roles of the human component in HRC and offering inconsistent insights on key
cognitive aspects. The impacts of HRC on worker safety pertaining to mental fatigue, stress, and attention remain largely
unexplored, presenting an urgent and critical need for research and intervention. Neglecting the understanding and analysis
of cognitive risk factors in HRC can lead to unforeseen safety hazards and health issues and further hinder the successful
adoption and efficiency of HRC in construction. Our long-term goal is to accelerate and pioneer the development of human-
centric approaches to achieving safe and efficient collaborations between humans and robots in the construction sector. This
includes a profound emphasis on the analysis of human cognitive factors to bolster construction occupational safety and
health, leading cutting-edge workforce development strategies. The overall objective of this application is to determine the
impact of levels of human-robot collaborations on workers’ (male and female) cognitive risk factors to enhance safety in
HRC. Two specific aims are proposed: (1) Determine the impact of the autonomy levels of HRC on construction workers’
mental fatigue, attention, and stress; (2) Determine the impact of the involvement of HRC in construction on male and
female workers’ cognitive risk factors and determine the difference (if there is). We will employ Virtual Reality to simulate
construction environments that encompass distinct levels of robot autonomy (including no robot). Participants, comprising
both males and females, will be equipped with wearable technologies that will continuously capture data (eye movements,
electroencephalography, heart rate, and skin temperature) pertaining to their cognitive states during the tasks. Both within-
subject and between-subject experimental designs will be utilized to gain comprehensive insights. The expected outcomes
are that we will have determined the influence of robot autonomy levels on construction workers' cognitive states and further
have gained insights into the differential impacts of HRC on male and female workers. The expected outcomes will
contribute to the r2p initiative by not only offering strong evidence to enhance saf...

## Key facts

- **NIH application ID:** 10951018
- **Project number:** 1R21OH012742-01
- **Recipient organization:** MISSISSIPPI STATE UNIVERSITY
- **Principal Investigator:** Jun Wang
- **Activity code:** R21 (R01, R21, SBIR, etc.)
- **Funding institute:** ALLCDC
- **Fiscal year:** 2024
- **Award amount:** $129,299
- **Award type:** 1
- **Project period:** 2024-09-30 → 2026-09-29

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10951018

## Citation

> US National Institutes of Health, RePORTER application 10951018, Human-Robot Collaboration in Construction: Assessing Cognitive Factors for Construction Workers Using Virtual Reality-Wearable Devices-Data Analytics Integrated Approach (1R21OH012742-01). Retrieved via MORVS 2026-10-25 from https://api.morvs.ai/grant/nih/10951018. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*