Wen-Chung Cheng
Papers
2
Total Citations
9
H-Index
2
About
Wen-Chung Cheng is a robotics researcher specializing in autonomous navigation, deep reinforcement learning, and mobile robot control. His work focuses on enabling robots to navigate complex, dynamic environments through intelligent decision-making and adaptive learning algorithms. Cheng's most notable contribution is the development of an automated learning and evaluation framework based on the Proximal Policy Optimization (PPO) method, which allows mobile robots to simultaneously pursue goal-seeking behaviors and avoid collisions in real-world settings—a paper that has garnered 6 citations since its 2024 publication. He has also advanced deep Q-learning techniques by introducing dynamic epsilon adjustment and path planner-assisted strategies for Turtlebot platforms, addressing common issues like repetitive circling behaviors and lengthy training convergence times. This work, published in 2023 with 3 citations, demonstrates his commitment to solving practical deployment challenges in physical robotics. Cheng's research bridges the gap between theoretical reinforcement learning algorithms and real-world robotic applications, making his findings valuable for both academic researchers and engineers developing autonomous service and industrial robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2