Portrait of Hsiu-Chin Lin

Hsiu-Chin Lin

Associate Academic Member
Assistant Professor, McGill University, School of Computer Science
Research Topics
Autonomous Robotics Navigation
Climate Change
Deep Learning
Out-of-Distribution (OOD) Detection
Reinforcement Learning
Robotics

Biography

Hsiu-Chin Lin is an assistant professor at the School of Computer Science and in the Department of Electrical and Computer Engineering at McGill University.

Her research spans model-based motion control, optimization and machine learning for motion planning. She is particularly interested in adapting robot motion in dynamic environments for manipulators and quadruped robots.

Lin was formerly a research associate at the University of Edinburgh and the University of Birmingham. Her PhD research at the University of Edinburgh was on robot learning.

Current Students

Amin Abyaneh
PhD - McGill University
Mohamad Danesh
PhD - McGill University
Website
Github
Google Scholar
Elham Daneshmand
PhD - McGill University
Co-supervisor :
Glen Berseth
Anas Houssaini
Master's Research - McGill University
Principal supervisor :
David Meger
Github
Zina Kamel
Master's Research - McGill University
Principal supervisor :
David Meger
Stanley Wu
Master's Research - McGill University

Publications

Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery
Amin Abyaneh
Mahrokh Ghoddousi Boroujeni
Hsiu-Chin Lin
Giancarlo Ferrari-Trecate
Imitation learning is a data-driven approach to learning policies from expert behavior, but it is prone to unreliable outcomes in out-of-sam… (see more)ple (OOS) regions. While previous research relying on stable dynamical systems guarantees convergence to a desired state, it often overlooks transient behavior. We propose a framework for learning policies using modeled by contractive dynamical systems, ensuring that all policy rollouts converge regardless of perturbations, and in turn, enable efficient OOS recovery. By leveraging recurrent equilibrium networks and coupling layers, the policy structure guarantees contractivity for any parameter choice, which facilitates unconstrained optimization. Furthermore, we provide theoretical upper bounds for worst-case and expected loss terms, rigorously establishing the reliability of our method in deployment. Empirically, we demonstrate substantial OOS performance improvements in robotics manipulation and navigation tasks in simulation.
2025-01-22
ICLR.cc/2025/Conference (poster)
doi.org
openreview.net
Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery
Amin Abyaneh
Mahrokh Ghoddousi Boroujeni
Hsiu-Chin Lin
Giancarlo Ferrari-Trecate
Imitation learning is a data-driven approach to learning policies from expert behavior, but it is prone to unreliable outcomes in out-of-sam… (see more)ple (OOS) regions. While previous research relying on stable dynamical systems guarantees convergence to a desired state, it often overlooks transient behavior. We propose a framework for learning policies using modeled by contractive dynamical systems, ensuring that all policy rollouts converge regardless of perturbations, and in turn, enable efficient OOS recovery. By leveraging recurrent equilibrium networks and coupling layers, the policy structure guarantees contractivity for any parameter choice, which facilitates unconstrained optimization. Furthermore, we provide theoretical upper bounds for worst-case and expected loss terms, rigorously establishing the reliability of our method in deployment. Empirically, we demonstrate substantial OOS performance improvements in robotics manipulation and navigation tasks in simulation.
2024-12-10
ArXiv (preprint)
arxiv.org
arxiv.org
A new species of Hoplostethus from Sumatra, eastern Indian Ocean, with comments on its most similar congeners (Trachichthyiformes: Trachichthyidae).
Yo Su
Alexander N. Kotlyar
Hsiu-Chin Lin
Toshio Kawai
HSUAN-CHING HO
2024-11-08
Journal of Fish Biology (published)
doi.org