Adaptive Informative Path Planning (AIPP) enables robots to efficiently collect data about unknown environments. Explore our survey on AIPP and its integration with robotic learning, authored by: Marija Popović, Joshua Ott, Julius Rückin, & Mykel Kochenderfer: arxiv.org/abs/2404.06940…

Linear Constrained Optimization is a powerful tool capable of solving a range of optimization tasks, with millions of variables and constraints. Discover more in Joshua Ott's lecture, covering KKT conditions, the simplex algorithm, and dual certificates. youtu.be/O0GN1AquD6o?si…

Real-world scenarios often have sensors that cannot operate concurrently due to energy, interference, or motion constraints. See how Joshua Ott addresses these challenges in trajectory optimization for the NASA VIPER Mission, accepted to IEEE-CoDIT: arxiv.org/abs/2404.18374

New book out from Jordan Ott on Reigniting American Innovation. We forget that just 40 years ago nearly every large company in the world was based in the United States. How do we reverse that tide? amazon.com/dp/B0D9WL4MMF

Congratulations to Joshua Ott on successfully defending his PhD on Autonomous Exploration of Unknown Environments! Efficient and safe exploration demands strategies that quantify uncertainty, optimize resources, and maximize information gain. Learn more: youtube.com/watch?v=UFA4zK…

Many problems, such as rover exploration, can be framed as informative path planning. Joshua Ott tackles the problem of finding an informative path through a graph with specified start and terminal nodes, within a maximum path length. Learn more: authors.elsevier.com/c/1jtVf3HdG3p4U~

Efficiently estimating system dynamics from data is essential for minimizing data collection costs and improving performance. We propose an approach that integrates informative input design into the Dynamic Mode Decomposition with control framework.

Joshua Ott recently gave an insightful talk on online planning and policy search in Stanford’s AA228/CS238: Decision Making Under Uncertainty course. Explore how these methods tackle high-dimensional problems: youtube.com/watch?v=iLMzsV…

In our first collaboration with the United States Air Force Test Pilot School and the DAF-Stanford AI Studio, we demonstrate that physics-informed Gaussian processes have the potential to accelerate flight test analysis. Learn more: arxiv.org/abs/2501.01000