Colorado State University · Dept. of Computer Science · An XR & Human-Centered AI Lab
We design and study gesture, speech, and gaze interaction for augmented and virtual reality. As intelligent systems become the interface, we're extending that work toward human-centered AI — technology that fits people, and that people can use naturally, effectively, and safely.
Papers
Three IEEE ISMAR 2026 Workshops, One Mission: Improving People’s Everyday Life with Extended Reality
Aug 16, 2026 →
Latest from the lab
Paper
Comparing Gesture Elicitation in Virtual and Augmented Reality
Aug 2, 2026 →
Latest from the lab
Grant
New NSF award: translating the science of learning into virtual reality
Oct 1, 2025 →
Latest from the lab
Grant
Ortega receives NSF CAREER award for multimodal interaction research
Mar 18, 2024 →
Latest from the lab
Project
Virtual nature: testing VR forest bathing for stress and recovery
Jan 22, 2024 →Natural User Interaction Laboratory
An XR & Human-Centered AI Lab · Colorado State University, Department of Computer Science
The latest
One living stream of publications, news, and project updates — the part of the site that stays current. Adding an item is one short file.
Three workshop papers at IEEE ISMAR 2026, and what their results mean: AR notifications without sound, virtual nature for stress, and VR for teaching …
We ran the same gesture elicitation study twice with the same 16 people, once in AR and once in VR. Most of the gesture vocabulary carried over. …
The lab is part of a new NSF I-USE collaborative award: Improving Conceptual Understanding of Invisible Physics by Translating the Science of Learning …
The National Science Foundation has awarded Dr. Francisco R. Ortega a CAREER grant to advance the science of multimodal and microgesture interaction. …
Lab life
Conferences, demos, and the team at work. A gentle rolling deck — pauses when you hover or focus, and holds still if you prefer reduced motion.
Research
How do we make interaction with 3D and immersive systems natural, low-effort, and available to everyone?
Given a headset and no instructions, what do people actually do? They reach, point, speak, and look, often at the same time. The hard part is that there is no single natural vocabulary waiting to be discovered. What people propose depends on how you ask them, what you show them, and what they have used before.
Augmented reality (AR) can put an arrow on the object you are looking for. The questions are where to place that arrow and whether the cue is correct — and what information-access effort costs. Related to visual search cues, we have notifications and timers: how do they compete for attention with the world they exist to explain, and where do we place them?
We have been looking at computer science education, wind and fluids engineering, and US Navy training systems to improve learning. We have used different approaches, including cognitive load theory.
Does a virtual forest do what a real one does? Nature contact lowers stress and restores attention, and extended reality makes it deliverable to a hospital room, a dorm, or a clinic. But nature is not one thing, and neither is the benefit. We ask which properties of a restorative environment survive being simulated in virtual reality, for whom, and on which measure.
Accessible XR is usually framed as adding a feature. Our evidence points somewhere else: what people need is control over the configuration. No single layout or interaction pattern serves everyone, and the arrangement that helps one person is often the one that gets in another’s way. The community is what matters, and in our research we always follow Charlton’s principle: “Nothing About Us Without Us.”
There are four high-level primary questions. (1) How can neuromorphic computing aid user interaction and decision making? (2) How is decision making affected as a user goes from a frontier LLM to a smaller model, and everywhere within that spectrum? (3) Agentic AI is set to become pervasive in many jobs. How does its use affect our cognitive load, and how can we improve the interfaces? And (4) how can neuromorphic computing and other AI paradigms help the user have a personalized interaction?
XR interaction depends on more than the headset and the interface. We have conducted work in networking and cybersecurity, and we are currently looking at privacy. For example, we studied the path from sensing and rendering to network transport and edge computation. Our goal is to support real-time collaboration, understand possible threats, and protect data.
Why it matters
The technical work points somewhere human — mental health, accessibility, and helping people learn and perform.
Forest-bathing environments that measurably reduce stress — exploring how virtual nature can support mental health.
Designing user interfaces for young adults with autism, with the Dan Marino Foundation — technology that meets people where they are.
Using VR to study how immersive experiences shape interest and retention in computing — so more students find their place in the field.
People
A multidisciplinary group — computer science, psychology, human factors, and more.
NUILab