Po-Jui Huang
Papers
3
Total Citations
83
H-Index
3
About
Po-Jui Huang is a robotics and autonomous systems researcher whose work sits at the intersection of reinforcement learning, robot navigation, and multi-robot coordination. His research tackles some of the most challenging problems in mobile robotics, including enabling robots to navigate complex, cluttered, and perceptually degraded environments with minimal human intervention. Huang's most influential contribution, "Curriculum Reinforcement Learning From Avoiding Collisions to Navigating Among Movable Obstacles," (37 citations) demonstrates how structured, progressive training regimens can dramatically accelerate learning in reinforcement learning agents operating in diverse real-world scenarios. His work on cross-modal contrastive learning (26 citations) addresses a critical limitation in autonomous vehicles by leveraging low-cost millimeter-wave radar for reliable navigation under adverse conditions such as fog, dust, and low light — environments where conventional camera-based systems fail. Further broadening his impact, Huang co-developed a heterogeneous team of ground vehicles and blimp robots for search-and-rescue operations in subterranean environments (20 citations), showcasing his ability to bridge theoretical learning frameworks with practical, mission-critical deployments. Together, his research portfolio reflects a sustained commitment to making autonomous robots safer, more adaptable, and deployable in the kinds of unpredictable conditions that matter most.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3