Cheng Yi

Papers

Total Citations

H-Index

About

Cheng Yi is a researcher advancing the frontiers of autonomous mobile robotics, with a core focus on intelligent path planning, deep reinforcement learning (DRL), and visual SLAM. His work addresses the critical challenge of enabling robots to navigate complex, dynamic environments with both global optimality and real-time adaptability. In his most cited work, "Research on Virtual Path Planning Based on Improved DQN" (13 citations), Cheng Yi demonstrates how an end-to-end Deep Reinforcement Learning approach can endow robots with human-level strategic capabilities for self-contained learning and environmental interaction. To bridge the gap between global planning and local obstacle avoidance, he proposed a novel fusion of an improved A* algorithm with the Morphin search tree, achieving both optimal routes and real-time responsiveness. Furthering his contributions to perception, his research on visual SLAM introduces an enhanced ORB algorithm that mitigates feature point clustering and redundancy, significantly improving the robustness of visual navigation. By integrating DRL with classical planning and perception methods, Cheng Yi’s work provides a comprehensive framework for next-generation autonomous systems, offering practical solutions for robots operating in unstructured, real-world settings.