Qingwu Fan
Papers
3
Total Citations
20
H-Index
3
About
Qingwu Fan is a researcher at the intersection of cognitive robotics, computational neuroscience, and artificial intelligence, with a primary focus on modeling fundamental learning mechanisms inspired by psychology and ethology. His most influential work, "A Cognitive Model Based on Neuromodulated Plasticity" (2016, 11 citations), proposes a unified framework integrating classical and operant conditioning—two cornerstone processes of associative learning—using neuromodulatory signals to bridge the gap between isolated models. This contribution offers a biologically plausible architecture for adaptive behavior in artificial agents. Fan further advanced operant conditioning modeling with "Operant Conditioning Learning Model Based on BP Network" (2014, 3 citations), which leverages back-propagation networks to implement Skinnerian reinforcement principles in cognitive robotics. More recently, his work on "A Real-time Visual SLAM Based on Semantic and Geometric Information in Dynamic Environments" (2024, 6 citations) extends his expertise into robust perception for autonomous systems, combining semantic understanding with geometric mapping. Collectively, Fan’s research demonstrates a sustained commitment to grounding AI learning algorithms in psychological theory, with applications ranging from developmental robotics to real-world navigation.
Research Focus
Key Achievements
Top Papers
- 1A Cognitive Model Based on Neuromodulated Plasticity11 citations · 2016
- 2
- 3Operant conditioning learning model based on BP network3 citations · 2014