Abstract: 

Foundation models, trained on vast and diverse data that capture broad aspects of the human experience, are at the heart of the ongoing AI revolution, transforming how we create, problem-solve, and work. These models—and the insights gained from developing them—are increasingly relevant to the advancement of autonomous robotic systems. In this talk, I will highlight how recent efforts to apply foundation models to embodied systems can be leveraged to push the frontiers of aerospace autonomy. The discussion will focus on two main thrusts. First, I will discuss how techniques traditionally developed in the foundation model literature can be adapted to enable reliable decision making in space, with an emphasis on spacecraft rendezvous and proximity operations. Next, I will discuss the opportunities presented by foundation models within data-driven autonomy stacks, ranging from automated data curation to serving as high-level reasoning modules.
 
Bio:

Dr. Daniele Gammelli is a Postdoctoral Scholar in the Department of Aeronautics and Astronautics at Stanford University. Since 2022, he has been a Research Fellow at the Center for Aerospace Autonomy Research (CAESAR) at Stanford and, until 2025, at the Center for Automotive Research at Stanford (CARS). He received his Ph.D. in Machine Learning and Mathematical Optimization from the Technical University of Denmark (DTU) in 2022, where his doctoral thesis was nominated for the DTU Best Thesis of the Year Award and the DTU Young Researcher Award. More broadly, Dr. Gammelli's research focuses on developing the algorithmic foundations and system-level methodologies that enable AI-powered autonomous systems to operate safely, efficiently, and reliably in high-stakes environments, with an emphasis on aerospace autonomy and next-generation mobility systems.

 
 
Suggested reading: 

Speaker-suggested readings: 
Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications. https://arxiv.org/abs/2408.05924
Language-Conditioned Safe Trajectory Generation for Spacecraft Rendezvous. https://semantic-guidance4space.github.io/
Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling. https://transformermpc.github.io/