Portrait of Hongbin Lin

Hello, I’m Hongbin (Ben) Lin

I work on force control and contact-rich manipulation: tasks where contact, not vision, decides whether the robot succeeds.
I am working at a Chinese embodied-AI startup as a Robotics Manipulation Engineer. Previously, I obtained my PhD degree from The Chinese University of Hong Kong, supervised by Prof. Kwok Wai Samuel Au. My background is in world models, reinforcement learning, surgical autonomy, and robot dynamics modeling; my current focus is force control and embodied VLA policies for contact-rich manipulation.
CV LinkedIn GitHub Scholar Email

Looking for collaborators

I am building an open benchmark for force-sensing contact-rich manipulation — a graded corpus of industrial threaded fasteners, a force-data metrology spec, and a pre-registered ablation on whether a real force sensor beats a joint-current estimate. Full rig under ¥30k; data and spec CC-BY-4.0, code Apache-2.0.
Force estimate vs. ground truth
a pre-registered three-way ablation on whether a 6-axis force/torque sensor actually beats a joint-current estimate for contact-rich policies.
A graded corpus of seized fasteners
industrial threaded joints graded by difficulty: infinitely resettable, cheap to run, and failure modes that a camera cannot see but a wrench signal can.
Force-data metrology
a spec for what makes a force dataset trustworthy: calibration traceability, sampling rate, units, and provenance.
I would like to hear from you if you work on force or tactile policies, contact-rich benchmarks, or force-data quality — or if you have access to industrial fastening or disassembly data or hardware. Reach me at hongbinlin@link.cuhk.edu.hk.

Publications

Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation
Hongbin Lin, Juan Rojas, Kwok Wai Samuel Au
arXiv, 2025
Paper
Visuomotor Grasping with World Models for Surgical Robots
Hongbin Lin, Bin Li, Kwok Wai Samuel Au
International Journal of Robotics Research (IJRR), 2025 (under review)
Paper
World Models for General Surgical Grasping
Hongbin Lin, Bin Li, Chun Wai Wong, Juan Rojas, Xiangyu Chu, Kwok Wai Samuel Au
Robotics: Science and Systems (RSS), 2024
Project Code
On the Monocular 3D Pose Estimation for Arbitrary Shaped Needle in Dynamic Scenes: An Efficient Visual Learning and Geometry Modeling Approach
Bin Li, Bo Lu, Hongbin Lin, Yaxiang Wang, Fangxun Zhong, Qi Dou, Yunhui Liu
IEEE Transactions on Medical Robotics and Bionics, 2024
Paper
End-to-end learning of deep visuomotor policy for needle picking
Hongbin Lin, Bin Li, Xiangyu Chu, Qi Dou, Yunhui Liu and Kwok Wai Samuel Au
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
Project Code Paper
Open-source High-precision Autonomous Suturing Framework With Visual Guidance
Hongbin Lin, Bin Li, Yunhui Liu, Kwok Wai Samuel Au
IEEE Int. Conf. Robotics and Automation (ICRA) Workshop, 2022
Project Code Paper
Learning deep nets for gravitational dynamics with unknown disturbance through physical knowledge distillation: Initial feasibility study
Hongbin Lin, Qian Gao, Xiangyu Chu, Qi Dou, Anton Deguet, Peter Kazanzides, K. W. Samuel Au
IEEE Robotics and Automation Letters, 2021 (presented at ICRA 2021)
Project Code Paper
A reliable gravity compensation control strategy for dVRK robotic arms with nonlinear disturbance forces
Hongbin Lin, C. W. Vincent Hui, Yan Wang, Anton Deguet, Peter Kazanzides, K. W. Samuel Au
IEEE Robotics and Automation Letters, 2019 (presented at IROS 2019)
Project Code Paper