Our research sits at the intersection of AI, safety engineering, and optimization. We focus on the hard problem of making sure AI systems do what they're supposed to do.

Picture a world where a self-driving shuttle navigates rush-hour traffic with your children in the back seat. Where AI helps doctors make split-second decisions in the emergency room. Where algorithms determine how to transition to clean energy without harming communities. In each scenario, the stakes couldn't be higher. Trust becomes everything.

Research Themes

Safety & Verification

AI Safety & Verification

Developing mathematical frameworks and validation methods to ensure AI systems are safe, reliable, and aligned with human values in high-stakes applications.

Simulation & Rare-Event Analysis

Accelerating safety evaluation through importance sampling and simulation techniques that find potential failures 1000x faster than conventional methods.

Autonomous Systems & Robotics

Building trustworthy autonomous decision-making systems for transportation, robotics, and human-robot collaboration with rigorous safety guarantees.

Optimization & Decision Making

Optimization & Decision Making

Designing algorithms for sequential decision-making under uncertainty, integrating reinforcement learning, Bayesian methods, and mathematical optimization.

Investment & Risk Management

Quantitative methods for risk assessment and investment decision-making in uncertain environments, from financial markets to infrastructure planning.

Applications & Sustainability

Supply Chain & Logistics

Modeling resilient supply chains using AI-driven optimization, particularly for critical minerals and energy systems during the global energy transition.

Critical Minerals & Energy Resilience

AI-powered exploration, extraction optimization, and supply chain modeling for critical minerals essential to clean energy technologies.

Climate Change & Sustainability

Applying AI to accelerate equitable energy transitions, optimize renewable resources, and ensure sustainable development that serves all communities.

Key Contributions

Deep Importance Sampling. A technique that finds potential failures in autonomous systems 1000x faster than conventional methods, enabling safety validation in weeks instead of decades.

Adaptive Meta-Learning for Safety. A framework that lets machine learning systems recognize situations beyond their training, creating a sixth sense for uncertainty. Recognized with a CPS Rising Star 2024 award.

Mineral-X Supply Chain Models. AI systems developed with Stanford Mineral-X that optimize for resilience and equity in critical mineral supply chains, ensuring the green revolution serves all communities.