Xiaoyan Fan
Papers
2
Total Citations
67
H-Index
2
About
Xiaoyan Fan is a researcher at the intersection of artificial intelligence, decision science, and product design innovation. Her work centers on developing intelligent frameworks that bridge semantic reasoning and machine learning for real-world applications. Fan’s most impactful contribution is a patent text-based conceptual design decision-making approach, which fuses incomplete evaluation semantics with scheme beliefs—a method that has garnered 64 citations since its 2024 publication. This work addresses critical gaps in how ambiguous or partial information can be systematically integrated into product design decisions, offering a novel pathway for AI-assisted innovation. In parallel, Fan has advanced reinforcement learning for robotics, proposing an improved Deep Deterministic Policy Gradient (DDPG) algorithm to overcome sparse reward challenges in robotic arm control. Her 2023 paper on this topic, though early in its citation trajectory, demonstrates her commitment to enhancing machine learning control performance. By combining patent analytics with reinforcement learning, Fan is shaping how autonomous systems and human designers collaborate, making her research particularly relevant for students and engineers exploring the frontiers of intelligent design and robotic autonomy.
Research Focus
Key Achievements
Top Papers
- 1
- 2