Muleilan Pei
Papers
2
Total Citations
100
H-Index
2
About
Muleilan Pei’s research lies at the intersection of robotics, reinforcement learning, and autonomous navigation, with a focus on enabling intelligent mobility in complex, unknown environments. Pei’s most influential work, an improved Dyna-Q algorithm for mobile robot path planning, tackles the challenging problem of navigating through environments with both static and dynamic obstacles. This paper has garnered 95 citations, reflecting its significance in advancing real-time, adaptive planning strategies. In complementary work, Pei explores quadruped robot locomotion on unstructured terrain using deep reinforcement learning, specifically leveraging the deep deterministic policy gradient (DDPG) algorithm to learn robust gait policies. This research pushes the boundaries of legged robotics, addressing the difficulty of maintaining stability and efficiency without prior terrain knowledge. Together, Pei’s contributions demonstrate a systematic approach to integrating reinforcement learning with robotic control, offering practical solutions for autonomous systems operating in unpredictable settings. Their work is particularly valuable for students and researchers interested in combining machine learning with real-world robotic applications, from search-and-rescue missions to planetary exploration.
Research Focus
Key Achievements
Top Papers
- 1
- 2