Giovanni Luca Marchetti

KTH Royal Institute of Technology

Papers

1

Total Citations

12

H-Index

1

About

Giovanni Luca Marchetti is a rising researcher in robotics and machine learning, whose work focuses on the critical challenge of enabling robots to learn safely from offline data. His primary research areas include offline reinforcement learning, distributional shift, and robotic policy generalization. Marchetti’s major contribution, articulated in his highly regarded paper “Back to the Manifold: Recovering from Out-of-Distribution States” (2022, 12 citations), addresses a fundamental bottleneck in deploying learned robotic policies: the dangerous divergence between training data and real-world states. He proposes a novel framework that allows a robot to recognize when it has strayed from the data manifold and, crucially, to recover autonomously without costly human intervention. This work is notable for its practical approach to bridging simulation and reality, offering a pathway toward safer, more robust autonomous systems. With his early-career impact already evident, Marchetti is a promising voice in the quest to make robot learning both data-efficient and deployment-ready.

Research Focus

Key Achievements

1
H-Index
1
Papers
12
Total Citations
12
Avg Citations/Paper
🏆 Most Cited Paper
Back to the Manifold: Recovering from Out-of-Distribution States
12 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: KTH Royal Institute of Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago