Xulong Li

Northeastern University, Beijing University of Posts and Telecommunications

Papers

Total Citations

H-Index

About

Xulong Li is a researcher focused on advancing intelligent robotics, with key contributions in robotic manipulation and autonomous navigation. His work centers on applying deep learning and reinforcement learning to solve fundamental challenges in robotics, particularly in grasp detection and path planning. Li's most cited paper, "Robotic Grasp Detection Using Light-weight CNN Model" (2020, 8 citations), introduces an accurate, real-time convolutional neural network that enhances robotic intelligence for industrial applications like assembly and sorting, addressing the limitations of traditional teach programming. His second notable work, "Path planning using deep reinforcement learning based on potential field in complex environment" (2021, 5 citations), innovatively combines artificial potential fields with Deep Deterministic Policy Gradient (DDPG) to define states, actions, and rewards, enabling robust navigation in complex environments. With a total of 13 citations across his top papers, Li demonstrates impactful, application-driven research that bridges theoretical advances with practical robotic systems. His work is particularly relevant for students and researchers interested in lightweight neural architectures for real-time control and hybrid reinforcement learning methods for autonomous decision-making in robotics.