Research
This page contains a curated list of my major research projects. I manually update this so it may be out-of-date. For the most up-to-date list of research and publications please see my Google Scholar page.
Robust AI Through Automated Red-Teaming
Automated red-teaming methods for failure discovery and validation of AI systems, with applications to language models and safety-critical domains including cybersecurity and mental health.
World Models for Robust Robotics
By applying principles of deep learning and representation learning, we can train models that learn to predict the future state of the world based on past actions and observations. These world models can be used for planning and control in complex, high-dimensional environments with inherent quantification of uncertainty, enabling robust decision-making and control for across a range of real-world robotic systems.
Space Safety
Application of formal decision-making frameworks, including Markov decision processes, to optimize operational safety of space systems and the sustainability of the space environment, with a focus on collision avoidance and space traffice management.
Automated Space Mission Operations and Task Planning
Algorithms for scheduling and task planning in Earth-observing satellite constellations, combining maximum independent set methods and Markov decision processes to optimize image collection across large satellite networks.
Astrodynamics
Application of formal decision-making frameworks, including Markov decision processes, to optimize operational safety of space systems and the sustainability of the space environment, with a focus on collision avoidance and space traffice management.
Ground Station Optimization
Integer programming approaches for selecting optimal ground station networks for low-Earth orbiting satellites, minimizing cost while maximizing data downlink coverage.
Robust Learning for AI Systems
For AI systems to be operationally effective they must be robust to variations encounted in real-world applications. This research explores methods for improving the robustness of AI systems, including techniques for training models that can generalize well to unseen data, and methods for improving the effectiveness of AI systems in real-world settings.
Other Research
Other research projects and publications in decision-making, planning, and related topics that don't fit into the other categories.