Pengcheng Kong

Changzhou University, Harbin Institute of Technology

Papers

Total Citations

H-Index

About

Pengcheng Kong is a robotics researcher whose work bridges bio-inspired design and intelligent control systems. His primary research areas include bio-inspired robotics, pneumatic actuation, and deep reinforcement learning for autonomous navigation. Kong made a significant contribution to the field of biomimetic robotics through his work on frog-inspired swimming robots powered by pneumatic muscles. His 2017 paper on the design and dynamic model of such a robot has garnered 27 citations, demonstrating its influence in the soft robotics community. He further refined this work with a subsequent optimization study, addressing the nonlinearity challenges inherent in pneumatic systems. More recently, Kong has advanced the field of autonomous navigation with his 2022 paper on improved path planning for indoor patrol robots using deep reinforcement learning, which has already accumulated 32 citations. In this work, he introduced an innovative algorithm that leverages Pan/Tilt/Zoom (PTZ) camera information to overcome the poor exploration and slow convergence typical of traditional deep reinforcement learning methods. Kong’s research is notable for its practical applications in both aquatic and terrestrial robotics, showcasing his versatility in tackling complex control and design challenges.