Po-Kai Chang

National Yang Ming Chiao Tung University

Papers

2

Total Citations

49

H-Index

2

About

Po-Kai Chang is a robotics researcher whose work focuses on autonomous navigation and long-duration aerial systems for challenging, unstructured environments. His key research areas include deep reinforcement learning for collision avoidance, multi-modal sensor fusion, and the design of resilient, resource-constrained robots. Chang’s most notable contribution is the development of a cross-modal contrastive learning framework that integrates lightweight, low-cost millimeter-wave radar with other sensor modalities. This approach enables unmanned vehicles to learn robust, collision-free navigation policies even in adverse environmental conditions where traditional vision-based systems fail—a critical advance for real-world deployment. His paper on this method has garnered 26 citations, reflecting its impact on the field. Additionally, Chang introduced the Duckiefloat, a collision-tolerant, autonomous blimp designed for long-term operation in subterranean environments. Inspired by the DARPA SubT Challenge, this platform addresses key challenges in search and rescue—mobility, perception, autonomy, and communication—by offering low power consumption and inherent resilience to collisions. With 23 citations, this work demonstrates his ability to create practical, innovative solutions for extreme conditions. Chang’s research bridges the gap between theoretical reinforcement learning and deployable robotic systems.

Research Focus

Key Achievements

2
H-Index
2
Papers
49
Total Citations
25
Avg Citations/Paper
🏆 Most Cited Paper
Cross-Modal Contrastive Learning of Representations for Navigation Using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions
26 citations · 2021
📈 Most Prolific Year: 2021 (1 Papers)
🤝 Key Collaborators: 13
🏛 Institutions: National Yang Ming Chiao Tung University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago