Yongdi Li

Papers

Total Citations

H-Index

About

Yongdi Li is a leading researcher in intelligent robotics, specializing in local path planning for mobile robots operating in unknown and complex environments. His work addresses critical challenges in autonomous navigation, particularly the issues of local deadlock and path redundancy that plague traditional planning algorithms. Li’s major contributions center on the innovative fusion of deep learning and reinforcement learning techniques. Notably, his 2021 paper on a "Fusion Method of Local Path Planning for Mobile Robots Based on LSTM Neural Network and Reinforcement Learning" has garnered 29 citations, demonstrating its influence in advancing robot perception and decision-making. In this work, he integrates Long Short-Term Memory networks with reinforcement learning to enhance environmental understanding and planning efficiency. Additionally, his "Double BP Q-Learning Algorithm for Local Path Planning of Mobile Robot" (9 citations) tackles the dimensionality disaster and poor generalization in state-rich environments by combining backpropagation neural networks with Q-learning. Li’s research is pivotal for developing more adaptive, robust autonomous systems, offering practical solutions for real-world robotic navigation challenges. His work continues to inspire new directions in intelligent control and machine learning integration.