Tian-Ao Ren

Chinese University of Hong Kong, Chinese University of Hong Kong, Shenzhen, Stanford University

Papers

Total Citations

H-Index

About

Tian-Ao Ren is a rising researcher at the intersection of soft robotics, medical endoscopy, and deep reinforcement learning. Their work focuses on solving the fundamental challenge of autonomous navigation for flexible, tendon-driven robots in unstructured and unknown environments—a critical bottleneck in both industrial manipulation and minimally invasive surgery. Ren’s major contributions include pioneering Sim-to-Real transfer methods that allow soft robots to learn precise navigation strategies from virtual environments, bypassing the need for complex physical models. Their 2023 paper on Sim-to-Real navigation for cable-driven soft robots (28 citations) demonstrates how virtual eye-in-hand vision can train collision-free steering policies that transfer effectively to real hardware. In the medical domain, Ren has advanced autonomous control of flexible robotic endoscopes for gastrointestinal procedures, using model-free deep reinforcement learning to overcome the control challenges posed by non-rigid systems. Their domain adaptation work for oropharyngeal organ segmentation (15 citations) further enables robust perception across simulated and real surgical scenes. With a growing citation record and publications spanning 2023–2024, Ren is establishing a reputation for making soft robotics more intelligent, autonomous, and clinically viable.