Menghao Wu

Papers

Total Citations

H-Index

About

Menghao Wu is a researcher advancing the frontiers of intelligent robotics through reinforcement learning and autonomous navigation. His work centers on developing more efficient, robust control algorithms for robots operating in complex, unknown environments. Wu’s key contributions include the Actor-Dueling-Critic method (2019, 21 citations), a novel model-free reinforcement learning approach that enhances policy learning by decoupling state and action value estimation, directly addressing the limitations of traditional value function methods in robotic control. He has also made significant strides in LiDAR-based Simultaneous Localization and Mapping (SLAM) by integrating semantic information into the LOAM framework (2021, 20 citations), enabling outdoor mobile robots to achieve more accurate and context-aware odometry and mapping. Additionally, Wu has tackled the challenge of obstacle avoidance with his Multi-Dimensional Actions Control approach (2021), which leverages reinforcement learning to handle symmetrical state spaces from axisymmetric distance sensors. Through these contributions, Wu is helping to build the next generation of autonomous systems that can perceive, learn, and navigate the physical world with greater intelligence and adaptability.