Shilin Shan

Papers

Total Citations

H-Index

About

Shilin Shan is a robotics researcher specializing in sensorless force estimation, human-robot interaction, and robotic manipulation. Their work addresses a critical challenge in modern robotics: enabling robots to sense and respond to contact forces without relying on expensive or fragile dedicated sensors. Shan's most cited contribution, "Fine Robotic Manipulation Without Force/Torque Sensor" (2023, 11 citations), demonstrated that precise manipulation tasks traditionally requiring six-axis force/torque sensors can be achieved through alternative computational approaches—a finding with significant implications for cost-effective industrial robotics. Building on this foundation, Shan has advanced deep learning-based methods for contact estimation, as seen in "Sensorless Estimation of Contact Using Deep-Learning for Human-Robot Interaction" (2024, 6 citations), which improves safety and responsiveness in collaborative human-robot tasks. Their subsequent work on fast payload calibration through model pre-training (2024, 6 citations) further accelerates practical deployment of sensorless systems in diverse settings. Collectively, Shan's research offers the robotics community accessible, robust alternatives to hardware-dependent force sensing, bridging the gap between high-performance manipulation and real-world affordability.