I-Jeng Wang

Johns Hopkins University, Johns Hopkins University Applied Physics Laboratory

Papers

Total Citations

H-Index

About

I-Jeng Wang is a robotics and artificial intelligence researcher whose work sits at the intersection of deep reinforcement learning, autonomous navigation, and human-robot interaction. His research addresses some of the most challenging problems in making robots operate intelligently and safely alongside people in real-world environments. Wang's most influential contribution, "Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks" (2017, 30 citations), demonstrated how DRL can enable robotic manipulators to perform reaching, collision avoidance, and grasping without requiring precise knowledge of arm structure or kinematics — a significant step toward adaptable, generalizable robotic control. This work has become a foundational reference in applied reinforcement learning for robotics. A recurring theme in Wang's research is socially intelligent navigation. His studies on group-aware robot navigation recognize that people naturally move in social clusters rather than as isolated individuals — a subtle but critical insight that prior work largely overlooked. His 2022 paper on group-aware navigation policies (19 citations) advanced this line of inquiry, building on earlier foundational work from 2020. His research on prediction-based uncertainty estimation further enhances robot safety in dynamic, crowded environments. Collectively, Wang's contributions are shaping the future of robots that can navigate and interact with humans naturally and responsibly.