Papers
6
Total Citations
134
H-Index
5
About
Jui-Te Huang is a robotics and autonomous systems researcher whose work spans assistive navigation, deep reinforcement learning, and robust sensing for real-world robotic deployments. His most recognized contribution, garnering 46 citations, introduced a deep reinforcement learning-based guiding robot incorporating UWB beacons and semantic feedback to empower blind and visually impaired individuals with independent mobility — a meaningful intersection of AI and social good. Huang has also advanced collision-free navigation under adverse environmental conditions through cross-modal contrastive learning with lightweight millimeter-wave radar, earning 26 citations and demonstrating his commitment to low-cost, practical sensing solutions. His work on the Duckiefloat blimp — a collision-tolerant, resource-constrained aerial robot designed for subterranean search and rescue — reflects his creativity in constrained-resource robotics, with 23 citations. Further extending this domain, he developed heterogeneous ground-and-blimp robot teams capable of autonomous multi-agent coordination in unknown environments. His recent research on multi-radar inertial odometry for 3D state estimation underscores a sustained focus on reliable perception in challenging conditions. Across his career, Huang's contributions bridge deep learning, novel sensing modalities, and human-centered robotics with genuine real-world impact.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6