Liancheng Shen

University of Chinese Academy of Sciences, Beijing Academy of Artificial Intelligence, Chinese Academy of Sciences

Papers

Total Citations

H-Index

About

Liancheng Shen is a rising researcher in intelligent robotic assembly, with a focus on contact-rich manipulation and reinforcement learning. His work addresses one of manufacturing’s most persistent challenges: the precise, automated assembly of irregular parts. Shen’s most-cited paper, “Review on Peg-in-Hole Insertion Technology Based on Reinforcement Learning” (2023), critically surveys how RL can overcome the limitations of traditional model-based methods, which struggle with complex contact states. This work has already garnered significant early attention. He further advances the field by proposing a framework to “learn latent causal factors from intricate sensor feedback” (2024), enabling robots to interpret noisy force and vision data during assembly tasks. His applied research includes designing a complete robot system for reorienting and assembling diverse components like screws and washers (2024), tackling challenges in precise orientation without specialized fixtures. Though early in his career, Shen’s integration of causal learning with RL for assembly—supported by his growing citation record—positions him as a promising voice in bridging simulation and real-world robotic dexterity.