Papers
4
Total Citations
45
H-Index
2
About
Daniele Gammelli is a researcher at the forefront of robotics and autonomous systems, with key contributions spanning model predictive control, reinforcement learning, and vision-language models. His work on **"Transformer-Based Model Predictive Control"** (2024, 35 citations) redefines trajectory optimization by leveraging sequence modeling to solve highly non-convex control problems, offering a scalable alternative to traditional MPC for general-purpose robot autonomy. In the domain of autonomous mobility, Gammelli’s **"Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems"** (2021, 6 citations) introduces a graph-based framework to dynamically coordinate fleets of self-driving vehicles, addressing the complex, real-time decision-making challenges of modern transportation networks. More recently, his pioneering **Space-LLaVA** project (2024–2025, 4 citations) adapts vision-language models for extraterrestrial applications, enabling robots to navigate unstructured space environments with contextual understanding. With a growing citation footprint and a focus on bridging foundational AI with practical robotics, Gammelli’s work is shaping the future of intelligent, autonomous systems—from Earth’s roads to the cosmos.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4