Tobia Marcucci
IIT@MIT, Italian Institute of Technology, University of Pisa, Piaggio (Italy)
Papers
7
Total Citations
277
H-Index
7
About
Tobia Marcucci is a leading researcher in robotics, specializing in motion planning and control for complex, contact-rich systems. His work centers on leveraging convex optimization to tackle fundamental challenges in robot autonomy, from navigating cluttered environments to managing multi-contact interactions. Marcucci’s most impactful contribution, “Motion planning around obstacles with convex optimization” (2023, 145 citations), introduces a framework that enables robots—from quadrotors to articulated arms—to design collision-free trajectories in high-dimensional spaces using fast, reliable convex solvers. He further advanced the field with “Approximate hybrid model predictive control for multi-contact push recovery in complex environments” (2017, 63 citations), addressing the hybrid dynamics of legged robots during physical interactions. His innovative two-stage optimization strategy for articulated bodies with unscheduled contact sequences (2016, 26 citations) improved robustness and efficiency in humanoid control. More recently, Marcucci has pioneered methods for approximating robot configuration spaces with convex sets using clique covers (2024, 13 citations) and developed tight convex relaxations for contact-rich manipulation (2024, 11 citations), pushing the boundaries of global motion planning. His work has earned over 270 citations, establishing him as a key figure in making optimization-based planning practical for real-world robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Motion planning around obstacles with convex optimization145 citations · 2023
- 2
- 3
- 4
- 5
- 6Towards Tight Convex Relaxations for Contact-Rich Manipulation11 citations · 2024
- 7Towards minimum-information adaptive controllers for robot manipulators7 citations · 2017