Research
Where the future unfolds
When you’ve led research and innovation for close to 80 years, it’s no longer work; it’s part of who you are.
At SRI, we’re part problem solver, part tech maverick. We’re always diving deeper and collaborating further to pioneer world-changing solutions for a safer, healthier, and more sustainable future.
Innovating in
Research, always applied
See how everyday exploration delivers in the real world.
-
SRI sleep expert Fiona Baker discusses menopausal insomnia
Researchers study how menopause can affect sleep and women’s physical and mental health.
-
SRI researchers use AI to study deadly viruses
Machine learning algorithms identify how hemorrhagic fever viruses hijack human cells.
-
Podcast: Supporting students with behavioral and emotional needs
SRI’s Carl Sumi discusses effective strategies and interventions for student support.
“Achievements like the first malaria medicine and key cancer-fighting drugs continue to power our passion to lead world-renowned research programs in sleep, addiction, menopause, treatment delivery, and other pressing concerns in our world today.”
Kathlynn BrownPresident, SRI Biosciences
How we work
SRI’s divisions and researchers work cross-functionally because we know that groundbreaking research and transformative solutions come to light when people come together to look at problems from new angles and perspectives.
Publications
-
SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments
We present SayNav, a new approach that leverages human knowledge from Large Language Models (LLMs) for efficient generalization to complex navigation tasks in unknown large-scale environments.
-
Machine Learning Aided GPS-Denied Navigation Using Uncertainty Estimation through Deep Neural Networks
We describe and demonstrate a novel approach for generating accurate and interpretable uncertainty estimation for outputs from a DNN in real time.
-
Non-Markovian Quantum Control via Model Maximum Likelihood Estimation and Reinforcement Learning
We propose a novel approach that incorporates the non-Markovian nature of the environment into a low-dimensional effective reservoir.