Guoming Liu

Papers

Total Citations

H-Index

About

Guoming Liu is a leading researcher in mobile robotics, with a primary focus on intelligent local path planning and autonomous navigation in complex, unknown environments. His work addresses critical challenges in real-time obstacle avoidance, particularly the "dead zone" and local minima problems that plague traditional methods. Liu's major contributions include pioneering the application of Long Short-Term Memory (LSTM) neural networks for path planning, enabling robots to learn and adapt to diverse environments without requiring environment-specific algorithms. He also developed the innovative Double BP Q-Learning algorithm, which fuses backpropagation neural networks with reinforcement learning to overcome the curse of dimensionality and poor model generalization. With his most-cited paper, "Local Path Planning of Mobile Robot Based on Artificial Potential Field," accumulating 26 citations, Liu's research has become foundational for engineers and roboticists seeking robust, adaptive solutions. His work is particularly notable for bridging classical control theory with modern deep learning, offering practical, scalable approaches that move beyond the limitations of traditional potential field methods.