Federico Pizarro Bejarano

Papers

Total Citations

H-Index

About

Federico Pizarro Bejarano is a robotics researcher whose work lies at the intersection of multi-robot systems, deep reinforcement learning, and embodied intelligence. His most impactful contribution, "Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions" (46 citations), addresses a critical challenge in robotics: enabling robot teams to explore cluttered, unstructured environments despite communication dropouts. By integrating macro-actions and high-level teammate intention modeling, his work provides a scalable framework for decentralized coordination—essential for search-and-rescue, space, and military applications. Beyond algorithmic advances, Pizarro Bejarano is a strong advocate for open science. His study "What Is the Impact of Releasing Code With Publications?" (4 citations) systematically analyzes code-sharing practices across machine learning, robotics, and control communities, highlighting its role in reproducibility and collective progress. Most recently, his work "ProDapt: Proprioceptive Adaptation Using Long-Term Memory Diffusion" introduces diffusion models that rely solely on proprioception (internal sensing) rather than cameras, enabling robust robot behavior in visually degraded environments like underwater or subterranean settings. By combining theoretical rigor with practical deployment challenges, Pizarro Bejarano’s research pushes toward resilient, autonomous systems that can operate where traditional sensors fail.