I am an Assistant Professor in the School of Electrical Engineering and Computer Science (EECS) at Oregon State University, where I lead the Intelligent and Reliable Autonomous Systems (IRAS) research group. I am also an affiliate member of the Collaborative Robotics and Intelligent Systems (CoRIS) Institute at Oregon State University. I earned my Ph.D. in Computer Science from the University of Massachusetts Amherst, where I was advised by Shlomo Zilberstein.
My research interests are in designing AI systems that are safe, reliable, and unbiased. My current research focus is on developing techniques for reliable decision-making in autonomous systems that operate in fully and partially observable environments. I am a recipient of the Outstanding Paper Award at RLC 2025, Outstanding Program Committee Member Award at ICAPS 2022, IJCAI 2020 Distinguished Paper Award, and a Rising Stars in EECS 2020 workshop participant. I serve as a Program Co-Chair of the International Conference on Automated Planning and Scheduling (ICAPS), 2026. During the summer of 2019, I interned in the Intelligent Systems Division at NASA Ames Research Center .
I designed and maintain a repository of negative side effects in AI systems. Consider contributing to our repository by letting us know about any negative side effects observed in a laboratory prototype or a deployed AI system.
Contact: sandhya.sai AT oregonstate.eduOffice: 3005 Kelley Engineering CenterRecent News
Winter 2026:
Our grape phenology prediction model has been deployed on AgWeatherNet! This model is now available to over 26000 growers to guide their vineyard management!
IRAS group member Alina Hyk recognized with OSU Honors College Joe Hendricks Scholarship for Academic Excellence! Congratulations, Alina!
Our paper on learning transferable latent user preferences accepted to the ICLR Workshop on “From Human Cognition to AI Reasoning: Models, Methods, and Applications”!
Our paper on reward learning from diverse forms of human feedback has been published on Frontiers in AI and Robotics!
Fall 2025:
Our paper on differential testing of autonomous systems accepted to AAAI Fall Symposium 2025!
Our paper on WOFOSTGym received the Outstanding Paper Award at RLC 2025!
Summer 2025:
Gave an invited talk on “Multi-Objective Planning with Contextual Preferences” at the RSS 2025 Workshop on Multi-Objective Optimization and Planning in Robotics.
Our paper introducing WOFOSTGym crop simulator for RL has been accepted to RLC 2025!