Thai Duong

Duncan Hall 3097 | thaiduong@rice.edu

thai.jpg

I am a postdoctoral research associate in the Kavraki Lab at Rice University, working with Prof. Lydia Kavraki on task and motion planning.

I obtained my Ph.D. from the Department of Electrical and Computer Engineering at University of California, San Diego. I worked on “Learning Environment and Dynamics Representations for Autonomous Robot Navigation” under the direction of Prof. Nikolay Atanasov at the Existential Robotics Laboratory. A long time ago, I worked as a software engineer at Microsoft. I obtained my M.S. degree from Oregon State University, Corvallis, Oregon and B.S. degree from Hanoi University of Science and Technology, Hanoi, Vietnam.

Research Interests

My research goal is to develop efficient, safe and reliable autonomous robot systems by integrating robot learning, planning and control in a principled manner. My work focuses on learning accurate robot dynamics and environment models that preserve the domain knowledge by construction for efficient motion planning and control. My techniques have been applied to multiple robot platforms with various applications such as: navigation and exploration with ground and aerial vehicles, aggressive maneuvers with legged robots, and task and motion planning with manipulators. My general research interests include robotics, machine learning, control theory, and optimization.

News

Dec 2025 Our survey paper on Classical, Learning, and Physics-Informed System Identification for Control has been submitted to Annual Reviews in Control.
Sep 2025 Our paper on Port-Hamiltonian neural ODEs on Lie groups has received the Best Paper Award from the IEEE RAS Technical Committee on Robot Control.
Sep 2025 Our paper on Learning IMU Bias Model for Visual Inertial Odometry has been accepted to RA-L.
Jun 2025 Our workshop “Fast motion planning and control in the era of parallelism” at RSS’25 has successfully concluded. Please check out the exciting talks and discussions here!
Jun 2025 Our paper on Physics-Informed Multi-agent Reinforcement Learning has been accepted to T-RO.
May 2025 Our paper on Port-Hamiltonian neural ODEs on Lie groups for robot dynamics learning and control has received an Honorable Mention of the 2024 T-RO King-Sun Fu Memorial Best Paper Award.
Jan 2025 Our paper on “Variational integrator-based trajectory optimization for legged robots” has been accepted to ICRA’25.
Nov 2024 Our paper on “Model Learning and Predictive Control for Dynamic Maneuvers on Legged Robots” has been accepted to RA-L.
Jul 2024 I joined the Kavraki Lab at Rice University as a postdoctoral researcher.
Jun 2024 Our paper on Port-Hamiltonian neural ODEs on Lie groups for robot dynamics learning and control has been accepted to T-RO.
May 2024 I successfully defended my PhD dissertation.
Jan 2024 Our papers on Optimal Planning with Large Language Model Guidance and Learning Dynamics from Sensor Observations have been accepted to ICRA’24.
Mar 2023 Our paper on Lie Group Forced Variational Integrator Networks has been accepted to L4DC’23.
Jan 2023 Our paper on Learning Distributed Multi-Robot Interactions has been accepted to ICRA’23.
Sep 2022 I gave a talk on “Learning and Control of Hamiltonian Dynamics on the SE(3) Manifold” at SIAM MDS’22.
May 2022 Our paper on Adaptive Control with Learned Disturbance Features has been accepted to L-CSS 2022 .
Apr 2022 Our paper on Sparse Bayesian Kernel-based Mapping has been accepted to T-RO.

Research Areas