From Simulation to Insight: VRAI on Unlocking the Value of XR Training Data

In this edition of Eirmersive’s Case Study Corner, Camille Donegan speaks with Niall Campion of VRAI about the growing role of data in simulation-based training, and why organisations adopting XR should be thinking about data capture from the very beginning.

VRAI began around ten years ago as a VR training company, initially focused on hazardous, remote and rarely encountered environments. Over time, the team recognised that VR headsets offered something potentially just as valuable as the immersive experience itself: rich contextual information about how a learner behaves during training.

Head tracking, eye tracking and other performance data could provide instructors with a much deeper understanding of what trainees were doing during a simulation and, importantly, help them understand why certain decisions were being made.

That insight ultimately led to HEAT, VRAI’s platform for capturing, storing, analysing and visualising data from training systems. Today, the company’s focus extends beyond VR alone, with HEAT designed to bring together information from different types of simulation devices and, in some cases, live training platforms.

Turning Training Data into Useful Insight

A key theme of the conversation is the difference between simply generating data and making that data genuinely useful.

As Niall explains, instructors are not data scientists and are often already operating under significant time pressure. Adding another layer of information is only valuable if instructors can quickly understand and use it.

HEAT addresses this by capturing information from different simulation systems, standardising it and presenting it through a dashboard designed to make the data easier to interpret.

For instructors, this can mean spending less time manually recording basic information during a session and more time observing higher-order behaviours such as decision-making, communication and interaction with others.

Combining XR with Human Performance Data

The discussion also explores VRAI’s strategic partnership with Varjo and what becomes possible when high-resolution XR hardware is combined with a layer of training analytics.

Varjo’s headsets can generate detailed eye and gaze-tracking data. Through HEAT, that information can be captured alongside simulation data and other inputs to help instructors understand not simply whether somebody completed a task, but aspects of how they performed during it.

One example discussed is cognitive load. VRAI can use eye-tracking data, alongside potential inputs from devices such as heart-rate monitors or smart watches, to provide instructors with an indication of the level of cognitive load experienced by a learner during different points in a training scenario.

The objective is not simply to generate more data. It is to give trainers additional evidence that can help them understand where a learner may be under-challenged or overloaded, and tailor subsequent training accordingly.

For existing Varjo customers, the partnership has also resulted in the HEAT Starter Kit, an introductory version of the platform that allows users to begin capturing and exploring data from their Varjo headset before moving to the fuller HEAT platform.

A Real-World Example with the Irish Defence Forces

The potential benefits become particularly tangible when Niall discusses a project involving VRAI, Varjo and the Irish Defence Forces.

The solution is used in training armoured vehicle drivers, enabling trainees to practise in XR rather than relying exclusively on physical vehicles.

According to Niall, the implementation changed the instructor-to-student ratio from one instructor to three students to one instructor to twelve students, effectively quadrupling instructor capacity.

This is particularly significant in an environment where highly experienced personnel are a limited resource. Increasing the number of trainees that can be supported by an instructor creates an opportunity to return experienced personnel to operational duties while maintaining training capacity.

Niall also cites a saving of approximately €52,000 per three-day training session by reducing the requirement to operate the physical vehicles during that training.

The project has also been independently studied with Learnovation and Trinity College, with Niall highlighting improved retention among learners.

Together, these outcomes underline an important point for organisations evaluating immersive training: the value proposition does not stop at realism or engagement.

XR can form part of a broader training infrastructure where instructor capacity, operational costs, learning outcomes and performance data can all be considered together.

Capture the Data from Day One

Perhaps the clearest takeaway from the interview is also one of the simplest: if you are investing in simulation, think about your data strategy from the beginning.

Niall argues that organisations too often implement an XR or simulation system first and only later realise that they should have been capturing the information it generated.

By then, potentially valuable historical training data has already been lost.

His advice is to design data capture into the system from the outset and, where possible, capture it in a standardised format that can subsequently be analysed.

That opportunity becomes even more significant as organisations begin exploring AI. Useful, domain-specific datasets accumulated through training could become an increasingly valuable strategic asset.

The same principle applies from a practical and procurement perspective. Retrofitting an analytics solution into an established simulation environment can introduce additional complexity. Thinking about simulation and its data layer together from the beginning creates a clearer route from training activity to measurable insight.

Building Trust Around Performance Data

Of course, gathering increasingly detailed information about individual performance also raises important questions around privacy, data ownership, security and responsible use.

VRAI’s position, according to Niall, is that the customer owns their data. He explains that deployments in sensitive environments can operate behind the customer’s firewall or within air-gapped environments.

He also discusses VRAI’s experience of going through an extensive ethics process with the RAF before beginning to capture participant data.

It is an important reminder that the conversation around data-driven immersive training cannot focus exclusively on what can be measured. Organisations also need to think carefully about how that information is collected, governed, interpreted and protected.

From Immersive Experience to Strategic Asset

The conversation with Niall captures an interesting evolution in enterprise XR.

The question is becoming less about whether an organisation can create a compelling immersive simulation and more about what it can learn from every training session that takes place within it.

For organisations already investing in XR training, that creates a deceptively simple question:

What happens to the data when the headset comes off?

VRAI’s approach is that it should not simply disappear. Captured responsibly and translated into useful insights, training data can become part of a much broader approach to understanding performance, improving learning and making better use of simulation investments.

And for organisations beginning that journey, Niall’s advice is refreshingly straightforward:

Start capturing the data from day one.

Now watch the full interview with Niall below.