Thai Duong

Thai Duong

Auto-generated profile, based on publicly available information

Thai Duong

Department of Computer Science, Rice University, Houston, TX, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2024 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
TDThai Duong
Thai Duong
AAAbdullah Altawaitan
Abdullah Altawaitan
JSJason Stanley
Jason Stanley
NANikolay Atanasov
Nikolay Atanasov
Accurate models of robot dynamics are critical for safe and stable control and generalization to novel operational conditions. Hand-designed models, however, may be insufficiently accurate, even after careful parameter tuning. This motivates the use of machine learning techniques to approximate the robot dynamics over a training set of state-control trajectories. The dynamics of many robots are described in terms of their generalized coordinates on a matrix Lie group, e.g. on $SE(3)$ for ground, aerial, and underwater vehicles, and generalized velocity, and satisfy conservation of energy principles. This paper proposes a port-Hamiltonian formulation over a Lie group of the structure of a neural ordinary differential equation (ODE) network to approximate the robot dynamics. In contrast to a black-box ODE network, our formulation embeds energy conservation principle and Lie group's constraints in the dynamics model and explicitly accounts for energy-dissipation effect such as friction and drag forces in the dynamics model. We develop energy shaping and damping injection control for the learned, potentially under-actuated Hamiltonian dynamics to enable a unified approach for stabilization and trajectory tracking with various robot platforms.

24 June 2025 in IEEE Transactions on Robotics
Verified
Journal Article
Open access
ESEduardo Sebastián
Eduardo Sebastián
TDThai Duong
Thai Duong
NANikolay Atanasov
Nikolay Atanasov
EMEduardo Montijano
Eduardo Montijano
CSCarlos Sagues
Carlos Sagues
The networked nature of multi-robot systems presents challenges in the context of multi-agent reinforcement learning. Centralized control policies do not scale with increasing numbers of robots, whereas independent control policies do not exploit the information provided by other robots, exhibiting poor performance in cooperative-competitive tasks. In this work we propose a physics-informed reinforcement learning approach able to learn distributed multi-robot control policies that are both scalable and make use of all the available information to each robot. Our approach has three key characteristics. First, it imposes a port-Hamiltonian structure on the policy representation, respecting energy conservation properties of physical robot systems and the networked nature of robot team interactions. Second, it uses self-attention to ensure a sparse policy representation able to handle time-varying information at each robot from the interaction graph. Third, we present a soft actor-critic reinforcement learning algorithm parameterized by our self-attention port-Hamiltonian control policy, which accounts for the correlation among robots during training while overcoming the need of value function factorization. Extensive simulations in different multi-robot scenarios demonstrate the success of the proposed approach, surpassing previous multi-robot reinforcement learning solutions in scalability, while achieving similar or superior performance (with averaged cumulative reward up to $\times 2$ greater than the state-of-the-art with robot teams $\times 6$ larger than the number of robots at training time). We also validate our approach on multiple real robots in the Georgia Tech Robotarium under imperfect communication, demonstrating zero-shot sim-to-real transfer and scalability across number of robots.

23 May 2022 in IEEE Control Systems Letters
Verified
Journal Article
Closed access
TDThai Duong
Thai Duong
NANikolay Atanasov
Nikolay Atanasov
Adaptive control is a critical component of reliable robot autonomy in rapidly changing operational conditions. Adaptive control designs benefit from a disturbance model, which is often unavailable in practice. This motivates the use of machine learning techniques to learn disturbance features from training data offline, which can subsequently be employed to compensate the disturbances online. This letter develops geometric adaptive control with a learned disturbance model 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 disturbance model identification stage , using a Hamiltonian-based neural ordinary differential equation (ODE) network trained from state-control trajectory data, and an online adaptive control stage , estimating and compensating the disturbances based on geometric tracking errors. We demonstrate our adaptive geometric controller in trajectory tracking simulations of fully-actuated pendulum and under-actuated quadrotor systems.

16 June 2022 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
TDThai Duong
Thai Duong
MYMichael Yip
Michael Yip
NANikolay Atanasov
Nikolay Atanasov
This article focuses on online occupancy mapping and real-time collision checking onboard an autonomous robot navigating in a large unknown environment. Commonly used voxel and octree map representations can be easily maintained in a small environment but have increasing memory requirements as the environment grows. We propose a fundamentally different approach for occupancy mapping, in which the boundary between occupied and free space is viewed as the decision boundary of a machine learning classifier. This work generalizes a kernel perceptron model which maintains a very sparse set of support vectors to represent the environment boundaries efficiently. We develop a probabilistic formulation based on relevance vector machines, handling measurement noise, and probabilistic occupancy classification, 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. The effectiveness of our mapping and collision checking algorithms is evaluated in tasks requiring autonomous robot navigation and active mapping in unknown environments.

18 December 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
CNChuong Nguyen
Chuong Nguyen
AAAbdullah Altawaitan
Abdullah Altawaitan
TDThai Duong
Thai Duong
NANikolay Atanasov
Nikolay Atanasov
QNQuan Nguyen
Quan Nguyen
Achieving both target accuracy and robustness in dynamic maneuvers with long flight phases, such as high or long jumps, has been a significant challenge for legged robots. To address this challenge, we propose a novel learning-based control approach consisting of model learning and model predictive control (MPC) utilizing a variable-frequency scheme. Compared to existing MPC techniques, we learn a model directly from experiments, accounting not only for leg dynamics but also for modeling errors and unknown dynamics mismatch in hardware and during contact. Additionally, learning the model with variable-frequency allows us to cover the entire flight phase and final jumping target, enhancing the prediction accuracy of the jumping trajectory. Using the learned model, we also design variable-frequency to effectively leverage different jumping phases and track the target accurately. In a total of 92 jumps on Unitree A1 robot hardware, we verify that our approach outperforms other MPCs using fixed-frequency or nominal model, reducing the jumping distance error $2-8$ times. We also achieve jumping distance errors of less than 3% during continuous jumping on uneven terrain with randomly-placed perturbations of random heights (up to 4 cm or 27% the robot's standing height). Our approach obtains distance errors of $1-2$ cm on 34 single and continuous jumps with different jumping targets and model uncertainties.

3 October 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
AAAbdullah Altawaitan
Abdullah Altawaitan
JSJason Stanley
Jason Stanley
SGSambaran Ghosal
Sambaran Ghosal
TDThai Duong
Thai Duong
NANikolay Atanasov
Nikolay Atanasov
Autonomous mobile robots operating in novel environments depend critically on accurate state estimation, often utilizing visual and inertial measurements. Recent work has shown that an invariant formulation of the extended Kalman filter improves the convergence and robustness of visual-inertial odometry by utilizing the Lie group structure of a robot’s position, velocity, and orientation states. However, inertial sensors also require measurement bias estimation, yet introducing the bias in the filter state breaks the Lie group symmetry. In this letter, we design a neural network to predict the bias of an inertial measurement unit (IMU) from a sequence of previous IMU measurements. This allows us to use an invariant filter for visual inertial odometry, relying on the learned bias prediction rather than introducing the bias in the filter state. We demonstrate that an invariant multi-state constraint Kalman filter (MSCKF) with learned bias predictions achieves robust visual-inertial odometry in real experiments, even when visual information is unavailable for extended periods and the system needs to rely solely on IMU measurements.