Max Robotics — Global Service Robot Directory + US Certification

About

Giuseppe Paolo is a robotics and artificial intelligence researcher whose work sits at the intersection of deep reinforcement learning, autonomous navigation, and embodied AI. He is perhaps best known for his pioneering 2017 contribution, "Virtual-to-Real Deep Reinforcement Learning," which demonstrated that mobile robots could learn mapless navigation using sparse laser range findings and continuous steering commands — a landmark paper that has accumulated over 800 citations and helped establish sim-to-real transfer as a central paradigm in robot learning. This work showed that agents trained entirely in simulation could generalize effectively to real-world environments, significantly lowering the barrier to deploying learned controllers on physical hardware. Paolo has also explored continuous control for multi-terrain tracked robots with flippers and developed data-driven approaches for interaction-aware pedestrian motion prediction in cluttered spaces, reflecting a sustained interest in making robots safer and more capable in human-shared environments. More recently, his 2024 paper "A Call for Embodied AI" positions physical grounding as essential to achieving artificial general intelligence, situating his research within broader philosophical and neuroscientific traditions. His body of work collectively advances the vision of robots that can perceive, learn, and act autonomously in complex, real-world settings.