Tommaso Guffanti
Vaughn College of Aeronautics and Technology, Stanford University
Papers
3
Total Citations
39
H-Index
2
About
Tommaso Guffanti is at the forefront of merging machine learning with model-based control and space robotics. His primary research areas include transformer-based trajectory optimization, model predictive control (MPC), and vision-language models for extraterrestrial applications. Guffanti’s most impactful contribution is his work on “Transformer-Based Model Predictive Control,” which reimagines constrained control by framing trajectory optimization as a sequence modeling problem—a novel approach that has already garnered 35 citations since 2024. This work addresses the longstanding challenge of solving non-convex optimization in real-time for autonomous robots. More recently, he has pioneered “Space-LLaVA,” a vision-language model specifically adapted for extraterrestrial environments, tackling the unique challenges of space robotics such as extreme conditions and limited data. With over 35 citations across his top papers, Guffanti’s research is shaping the future of autonomous systems both on Earth and in space. His work stands out for its bold integration of foundation models into safety-critical control, positioning him as a rising leader in intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3