Federico Landi

Papers

Total Citations

H-Index

About

Federico Landi is a researcher advancing the frontiers of embodied AI and autonomous navigation, with a primary focus on how intelligent agents explore and understand indoor environments. His most influential work, "Focus on Impact: Indoor Exploration With Intrinsic Motivation" (2022, 19 citations), tackles a fundamental challenge in robotics: enabling agents to efficiently explore unknown spaces without external rewards. Landi’s key contribution lies in designing hierarchical deep reinforcement learning (DRL) architectures that use intrinsic motivation—rewarding agents for actions that produce meaningful changes in their environment—rather than relying solely on sparse external signals. This approach dramatically improves exploration efficiency and robustness in complex, cluttered indoor settings. By bridging the gap between simulated training and real-world deployment, his work has direct implications for autonomous robots, from search-and-rescue operations to domestic service robots. Landi’s research exemplifies how principled algorithmic design can push the boundaries of what autonomous systems can achieve, making him a rising voice in the intersection of reinforcement learning, computer vision, and robotics.