People
AI for space and sustainability
Human-centric artificial intelligence
Machine learning for safety validation
Human performance estimation and optimization
Robotic manipulation
Safe autonomous systems
AI safety
Safety verification of nonlinear systems
AI evaluations (Stanford Interdisciplinary Graduate Fellowship)
Decision making for space applications (Amazon Fellowship)
Improving resilience in learning-based autonomy in extreme environments (Stanford Graduate Fellowship)
Multiagent planning (Knight-Hennessy Fellowship)
Decision making for spacecraft collision-avoidance (Hertz/NDSEG Fellowships)
Decision making for space operations (Stanford Graduate Fellowship)
Flexible representations of general intelligence
Multiagent systems (Knight-Hennessy)
Sequential decision making in high dimensional spaces
Constrained decision problems
Satellite maneuver planning and collision avoidance
AI safety and security policy
Optimal decision making for aquaculture
Automated driving
Responsible AI
Language models for decision support (REU)
Language red-teaming
Failure prediction in language model reasoning
Machine learning for aviation
Multi-agent planning
Scientific surrogate models
Validation of safety critical systems
Ground station optimization
Aircraft state estimation
Deep reinforcement learning and optimization
Computational intelligence, task-level robotics, and multiagent systems