My lab group investigates how machine learning, foundation models, reinforcement learning, and distributed intelligence can be combined with next-generation networks to enable real-time perception, adaptive control, and trustworthy decision-making under dynamic and resource-constrained environments.

Our group studies how Extended Reality (XR), including augmented reality, virtual reality, and mixed reality, can be combined with AI to support learning, collaboration, and social connection. Our work focuses on the design and evaluation of human-centered AI systems, including pedagogical AI agents, AI-supported XR tools, and immersive systems for AI literacy.

We conduct research on the following topics: agentic AI for digital safety, multimodal AI for video understanding, AI-powered content moderation and trust and safety, smart home security and privacy assistants, human-centered AI for security and privacy, and privacy-aware and trustworthy AI systems.

The Real-Time Intelligent Systems Lab (RTIS Lab) develops trustworthy, efficient, and deployable intelligent systems that integrate artificial intelligence, real-time computing, and cyber-physical systems. Our research focuses on enabling AI-powered systems to operate safely and reliably in resource-constrained and mission-critical environments. Current research areas include autonomous and robotic systems, embedded and edge AI, trustworthy and resilient machine learning, AI-enabled healthcare and wearable sensing, digital twins, and intelligent cyber-physical systems. We combine advances in AI, systems, and formal methods to address challenges in safety, timing correctness, robustness, and resource efficiency, with applications ranging from autonomous vehicles and robotics to healthcare technologies and smart infrastructure.

Our lab focuses on the relationship between applied behavior analysis and machine learning. We innovate in machine reinforcement learning using inspiration from how animals learn. Similarly, we enhance our understanding of animal behavior through the development of novel machine learning methods to interpret behavior.

The iEXCEL (Innovation for EXperiential Complex, open-Ended Learning) Lab designs and studies technology-driven open-ended learning environments, including immersive simulations, serious games, and museum exhibits, aimed at engaging learners with complex, real-world STEM challenges such as climate change and antimicrobial resistance. AI and machine learning serve as core methodological tools within this mission: the lab applies computer vision, causal modeling, multimodal models, learning analytics, and large language models to analyze learner behavior, model problem-solving strategies, and generate adaptive educational feedback. The lab also leverages network science and graph-based machine learning to study interdisciplinary research communities and other natural and social networks.

The WSPR Laboratory models, designs, builds, and validates technology that protects users, systems, and networks from malicious and privacy-infringing acts. The group’s faculty members and affiliated students work on all areas of cybersecurity, from designing new cryptographic constructs to ensure protected execution of code to empirical studies on how software is secured by developers; from finding flaws in existing operating systems to building systems resilient from known attacks; from detecting malicious activity such as malware and denial of service attacks to building networks and mechanisms to prevent abuse. The WSPR Lab works to secure all types of computer systems, from legacy telephone networks to emerging technologies like smartphones and Internet of Things devices.

Through the CEREAL Lab, Dr. Catete and her students investigate the design, implementation, and evaluation of AI education across secondary and undergraduate contexts. Using mixed-methods approaches, the lab examines which AI concepts are foundational at each stage of the learning pipeline, and which concepts are essential for students who are not pursuing formal computer science degrees. Interviews with stakeholders, administrators, and alumni surface industry needs and reveal critical gaps in AI skills and content knowledge. Across all projects, the lab is committed to equipping the next generation of learners, regardless of career path, with the AI literacy and skills needed to thrive in an AI-integrated workforce.

The Help through INTelligent Support (HINTS) Lab, directed by Dr. Thomas Price, works to develop learning environments that automatically support students with AI and data-driven help features. With a focus on computing education, our goal is to reimagine programming environments as adaptive, interactive systems that help students to pursue learning goals that are meaningful to them. We believe that every student should be able to learn computing with the support they need to be successful, working on projects that match their values and interests. Our research emphasizes practical methods that can scale to new classrooms and contexts, without placing additional burden on instructors.

The Synergistic Sensing and Computing System (SSCS) Lab at NC State develops AI-enabled sensing and computing systems for human-centered applications. The lab combines sensor hardware, AI and machine learning, and systems design to turn data from wireless, wearable, and mobile sensors into reliable inference about human behavior, physiology, and context. We focus on health monitoring, human-computer interaction, and security, with activities spanning new sensing pipelines, AI-enabled infrastructure, and end-to-end system prototyping for real-world use.

Our group includes doctoral, master’s, and undergraduate researchers working cohesively on theory and systems for next-generation AI solutions in networking, sensing, and computing. Beyond fundamental AI systems and networking research, we explore applied AI use cases in advanced engineering systems such as next-generation wireless and quantum systems, as well as in various application domains including agriculture, forestry, disaster response, and more.

The Generative Intelligent Computing (GIC) Lab develops trustworthy, efficient, and adaptive AI systems, with a focus on large language models, agentic AI, robust machine learning, and resource-efficient deep learning. The lab studies how AI systems can reason, use tools, coordinate with other agents, adapt to changing environments, and operate reliably under real-world constraints such as limited data, distribution shifts, and computational budgets. Current research activities include LLM agents, retrieval- and tool-augmented reasoning, multi-agent systems, model compression, adaptive inference, uncertainty-aware learning, open-world adaptation, and AI applications in scientific discovery, education, and cyberinfrastructure.

The Software Intelligence and Modernization Lab (SIM Lab) advances the state of the art in software evolution through the integration of software engineering and artificial intelligence. Our research addresses legacy system modernization, software quality, variability management, model-driven engineering, and AI-powered software development and maintenance.

The AERIS Lab (Autonomous Experimental Robotics and Intelligent Systems), directed by Dr. Bradley, develops theory, algorithms, and systems for autonomous vehicles, primarily unmanned aircraft systems, operating in complex, resource-constrained environments. Its AI-related research centers on learning-enabled and assured autonomy: reachability-based control barrier functions and self-triggered communication for safe multi-agent coordination under contested or adversarially manipulated conditions; deep reinforcement learning for agile flight control; learned perception and perception-aware planning for GPS-denied geo-localization; and reinforcement- and consensus-based cooperative control for UAS teams and swarms. A unifying theme is the co-regulation of cyber-physical resources, jointly managing computation, communication, and physical control so that learning-enabled systems remain real-time, verifiable, and reliable on board. The lab emphasizes experimental validation, testing these methods on custom UAS and tethered robotic platforms through multi-hour field demonstrations, and applies them across defense, agriculture, and environmental monitoring. Current activities span NSF-, USDA-, and DoD-sponsored projects and an NSF Research Experiences for Undergraduates (REU) program training the next cohort of autonomy researchers.

Our group conducts fundamental AI research, especially for trustworthy, interpretable, and efficient AI and deep learning. Our interest lies at the intersection of failure modes, safety risks, and vulnerabilities and the efficiency of deep learning.

STAC Lab research, sponsored by NSF, NIFA, DOE, and IARPA, advances both fundamental and applied machine learning and artificial intelligence to tackle pressing environmental and societal challenges. The lab’s innovations span spatiotemporal anomaly detection, change detection, complex object classification, semi-supervised learning, multi-source data fusion, and computational steering, with applications ranging from meteorological and remote sensing analysis to large-scale crop and forest classification.