Papers
6
Total Citations
50
H-Index
4
About
Dezhong Zhao is an emerging researcher at the forefront of human-robot collaboration and intelligent task allocation, with a focused body of work that bridges multi-agent systems, deep reinforcement learning, and personalized human-robot interaction. His most influential contributions center on the challenge of coordinating multi-human multi-robot (MH-MR) teams — complex, heterogeneous systems that combine diverse human expertise with robotic capabilities to tackle large-scale missions. His attention-enhanced hierarchical reinforcement learning framework for initial task allocation has garnered significant attention, accumulating over 19 citations since 2024 and establishing him as a key voice in this specialized domain. Beyond team coordination, Zhao has made notable strides in preference-based reinforcement learning, developing PrefCLM, a system that leverages crowdsourced large language models to dramatically reduce the human feedback burden in robot training — a practical innovation with broad implications for scalable robot learning. His work on personalization in human-robot interaction further demonstrates his commitment to building adaptive, human-centered robotic systems. With nearly 50 citations across a compact publication record spanning just two years, Zhao's research trajectory suggests a researcher rapidly shaping how humans and robots learn to work together effectively in dynamic, real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6