Papers
170
Total Citations
5,683
H-Index
37
About
Marco Pavone is a leading robotics and autonomous systems researcher whose work spans autonomous mobility, motion planning, and learning-based control. Perhaps best known for his foundational contributions to autonomous mobility-on-demand (AMoD) systems, Pavone pioneered queueing-theoretical and model predictive control frameworks for coordinating fleets of self-driving vehicles in urban environments — work that has garnered over 350 and 150 citations respectively and directly influenced how researchers and industry approach robotic transportation logistics. His 2011 survey on dynamic vehicle routing (222 citations) remains a cornerstone reference for multi-robot task planning. Beyond mobility systems, Pavone has made significant strides in trajectory optimization, with his convex optimization tutorial (233 citations) becoming an essential resource for engineers designing dynamically feasible paths for autonomous systems. His more recent research reflects a bold pivot toward integrating machine learning with classical control, including neural model predictive control for agile quadrotors, latent-space motion planning, and natural language-driven task planning through Text2Motion. Across more than a decade of research, Pavone has consistently bridged rigorous mathematical theory with practical robotic applications, establishing himself as a uniquely versatile and influential voice in modern autonomy research.
Research Focus
Key Achievements
Top Papers
- 1
- 2Robotic load balancing for mobility-on-demand systems286 citations · 2012
- 3
- 4Dynamic Vehicle Routing for Robotic Systems222 citations · 2011
- 5Text2Motion: from natural language instructions to feasible plans197 citations · 2023
- 6
- 7Robust online motion planning via contraction theory and convex optimization183 citations · 2017
- 8Robot Motion Planning in Learned Latent Spaces158 citations · 2019
- 9Model predictive control of autonomous mobility-on-demand systems152 citations · 2016
- 10