Thai Duong

I am a Ph.D. student in the Department of Electrical and Computer Engineering at University of California, San Diego. I work at the Existential Robotics Laboratory and am fortunate to be advised by Prof. Nikolay Atanasov.

Before moving to San Diego, 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.

Email  /  Google Scholar  /  Github  /  Blog

profile photo
Recent News
Research Interests

I am interested in robotics, machine learning, control theory, and optimization. My work focuses on robots' understanding of the environments, e.g. probablistic mapping, navigation and exploration; and of their own dynamics model, e.g. robot dynamics learning and model-based reinforcement learning. I am also interested in modeling uncertainty in map representations and robots' dynamics for safe and active planning and control.

Publications
Projects for robot dynamics learning and control

Learning Adaptive Control for SE(3) Hamiltonian Dynamics
Thai Duong, Nikolay Atanasov
In submission, 2021.
website / video / arXiv

This paper develops adaptive geometric control for rigid-body systems, such as ground, aerial, and underwater vehicles, that satisfy Hamilton's equations of motion over the SE(3) manifold. Our design consists of an offline system identification stage, followed by an online adaptive control stage. In the first stage, we learn a Hamiltonian model of the system dynamics using a neural ordinary differential equation (ODE) network trained from state-control trajectory data with different disturbance realizations. The disturbances are modeled as a linear combination of nonlinear descriptors. In the second stage, we design a trajectory tracking controller with disturbance compensation from an energy-based perspective. An adaptive control law is employed to adjust the disturbance model online proportional to the geometric tracking errors on the SE(3) manifold.



Trajectory tracking + learned dynamics

Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control
Thai Duong, Nikolay Atanasov
RSS, 2021.
website / video / arXiv

The dynamics of many robots, including ground, aerial, and underwater vehicles, are described in terms of their SE(3) pose and generalized velocity, and satisfy conservation of energy principles. This paper proposes a Hamiltonian formulation over the SE(3) manifold of the structure of a neural ordinary differential equation (ODE) network to approximate the dynamics of a rigid body. In contrast to a black-box ODE network, our formulation guarantees total energy conservation by construction. We develop energy shaping and damping injection control for the learned, potentially underactuated SE(3) Hamiltonian dynamics to enable a unified approach for stabiliziation and trajectory tracking with various platforms, including pendulum, rigid-body, and quadrotor systems.


Data collection from manual flights

Projects for environment understanding
Autonomous Navigation in Unknown Environments with Sparse Bayesian Kernel-based Occupancy Mapping
Thai Duong, Michael Yip, Nikolay Atanasov
Submitted to TRO, 2020
website / video / arXiv

This paper focuses on online occupancy mapping and real-time collision checking onboard an autonomous robot navigating in a large unknown environment. We develop a probabilistic formulation based on Relevance Vector Machines, allowing probabilistic occupancy classification and supporting autonomous navigation. We provide an online training algorithm, updating the sparse Bayesian map incrementally from streaming range data, and an efficient collision-checking method for general curves, representing potential robot trajectories.

Autonomous Navigation in Unknown Environments using Sparse Kernel-based Occupancy Mapping
Thai Duong, Nikhil Das, Michael Yip, Nikolay Atanasov
ICRA, 2020
website / video / arXiv

We propose a new map representation, in which occupied and free space are separated by the decision boundary of a kernel perceptron classifier. We develop an online training algorithm that maintains a very sparse set of support vectors to represent obstacle boundaries in configuration space. We also derive conditions that allow complete (without sampling) collision-checking for piecewise-linear and piecewise-polynomial robot trajectories.

Projects for robot safety
Safe Robot Navigation in Cluttered Environments using Invariant Ellipsoids and a Reference Governor
Zhichao Li, Thai Duong, Nikolay Atanasov
ArXiv, 2020
arXiv

We consider a control-affine nonlinear robot system subject to bounded input noise and rely on feedback linearization to determine ellipsoid output bounds on the closed-loop robot trajectory under stabilizing control. A virtual governor system is developed to adaptively track a desired navigation path, while relying on the robot trajectory bounds to slow down if safety is endangered and speed up otherwise. The main contribution is the derivation of theoretical guarantees for safe nonlinear system path-following control and its application to autonomous robot navigation in unknown environments.

Projects from the old days
Location-assisted coding for FSO communication
Duong Nguyen-Huu, Thai Duong, Thinh Nguyen
IEEE Transactions on Communications, 2017
Q2SWinet, 2015
journal version / conference version

We describe WiFO, a hybrid WiFi and FSO high-speed wireless local area network of femtocells that can provide high bit rates while maintaining seamless mobility. Importantly, we introduce a novel location-assisted coding (LAC) technique, based on which, the number of novel rate allocation algorithms is proposed to increase throughput and reduce interference for multiple users in a dense array of overlapped femtocells.

Adiabatic Markov Decision Process: Convergence of Value Iteration Algorithm
Thai Duong, Duong Nguyen-Huu, Thinh Nguyen
Journal of Dynamic Systems, Measurement, and Control, 2016
CISS, 2013
journal version / conference version

We study the performance of the classic value iteration algorithm for solving an MDP problem under nonstationary environments, characterized by an adiabatic evolution inspired from quantum mechanics. The performance is measured in terms of the convergence rate to the optimal average reward. We show two examples of queuing systems that make use of our analysis framework.

Data Collection in Sensor Networks via the Novel Fast Markov Decision Process Framework
Thai Duong, Thinh Nguyen
IEEE Transactions on Wireless Communications, 2015
ICCCN, 2014
journal version / conference version

The goal is to find a “fast” optimal movement pattern/policy of data collection in a sensor networks that optimizes for the costs and rewards in non-stationary environments. We formulate and solve this problem using a novel optimization framework called fast Markov decision process (FMDP) that incorporates the notion of mixing time and allows for the trade-off between the optimality and the convergence rate to the optimality of a policy.

Virtual machine placement via Q-learning with function approximation
Thai Duong, Yu-jung Chu, Thinh Nguyen, Jacob Chakareski
GLOBECOM, 2015
pdf

This paper formalizes an optimization framework and develops corresponding algorithmic solutions using Markov Decision Process and Q-Learning for virtual machine/service placement and migration for distributed computing in time-varying environments. Importantly, the knowledge of the underlying topologies of the computing infrastructure, the interaction patterns between the virtual machines, and the dynamics of the supported applications will be formally characterized and incorporated into the proposed algorithms.


Template borrowed from Jon Barron.