University of Utah

The Aligned, Robust, and Interactive Autonomy (ARIA) Lab is a research group in the Kahlert School of Computing and the Robotics Center at the University of Utah, directed by Assistant Professor Daniel S. Brown. The lab's overarching goal is to develop robots and other AI systems that can safely and efficiently interact with, learn from, teach, and empower human users. Core research areas include reward and preference learning, imitation learning, human-in-the-loop reinforcement learning, Bayesian inverse reinforcement learning, and AI safety. The lab develops both algorithmic methods and theoretical guarantees, deploys work on physical robot platforms, and conducts user studies to understand human factors in human-robot and human-AI systems. Daniel Brown completed his Ph.D. in Computer Science at UT Austin in 2020 and his postdoctoral fellowship at UC Berkeley in 2022, then joined the University of Utah. He was named a Robotics Science and Systems Pioneer in 2021 and received an AAAI New Faculty Highlight Award in 2025. In 2024, he received an NIH Trailblazer award (joint with mechanical engineering professor Haohan Zhang) for research on a powered neck exoskeleton using gaze-based reward learning. Open Philanthropy has supported the lab's AI safety-relevant work with two grants: $31,773 in August 2023 to develop a course on human-AI alignment, and $140,000 in May 2024 to support research on verifying the extent to which AI systems are aligned with human values. The lab is affiliated with the University of Utah's One-U Responsible AI Initiative.