Papers
5
Total Citations
39
H-Index
3
About
Ruihan Zhao is a rising researcher at the intersection of robotics, reinforcement learning (RL), and human–robot collaboration (HRC). Their work centers on making robotic systems both more intelligent and more adaptable, with a strong emphasis on data efficiency and human-centric design. A key contribution is the development of the "Safety-Efficiency Integrated Assembly" framework, a next-generation adaptive task allocation and planning system for HRC that aims to balance productivity with worker well-being—a timely contribution to sustainable manufacturing. Zhao has also advanced sample-efficient robot learning, showing how contrastive pre-training and data augmentation can bridge the gap between simulated and real-world RL, a critical step for practical deployment. In hierarchical imitation learning, they introduced skill transition models that enable agents to solve long-horizon tasks and generalize to unseen scenarios using few demonstrations. Their work on compositional RL, framed through the "Reduce, Reuse, Recycle" lens, tackles the fundamental challenge of task decomposition for complex behaviors. With over 39 total citations and multiple publications in 2025 alone, Zhao is establishing a reputation for rigorous, application-driven research that directly addresses the safety, efficiency, and adaptability challenges of next-generation robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Hierarchical Few-Shot Imitation with Skill Transition Models6 citations · 2021
- 4
- 5