conference & journal articles

2026

1. Humanoids

   

   Robust and Optimized Aggressive Standing-Up Maneuvers for Humanoid Robots across Diverse Terrains

   Chuong Nguyen^*, Quang Huy Dao^*, Loc Pham, Truong Nguyen, and Quan Nguyen

   In IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2026

   Accepted.

   Abs Bib Video Website

   Aggressive standing-up for full-size humanoid robots on grass, debris, and other uneven surfaces. The method optimizes contact timing and a whole-body trajectory, then tracks it with a learned controller so the robot can get up from supine and prone postures, including martial-arts-style maneuvers. The study compares this approach with trajectory optimization paired with linear and nonlinear model predictive control.

   @inproceedings{dao2026standing,
     title = {Robust and Optimized Aggressive Standing-Up Maneuvers for Humanoid Robots across Diverse Terrains},
     author = {Nguyen, Chuong and Dao, Quang Huy and Pham, Loc and Nguyen, Truong and Nguyen, Quan},
     booktitle = {IEEE-RAS International Conference on Humanoid Robots (Humanoids)},
     year = {2026},
     note = {Accepted.}
   }

2. Humanoids

   

   Ukemi-SafeFall: An Ukemi-inspired Injury-Aware Falling and Recovery

   Anh Duc Tran^*, Anh-Quang Vu^*, Loc Pham, Trong Hieu Nguyen, Chuong Nguyen Le, Quang Huy Dao, Hoang Vu Dao, Van-Truong Nguyen, Chuong Nguyen, Pham Tuyen Le, and Quan Nguyen

   In IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2026

   Accepted.

   Abs Bib Website

   Ukemi-inspired falling and recovery for a humanoid, so the robot can hit the ground and stand back up while limiting impact. Accepted at Humanoids.

   @inproceedings{vu2026ukemi,
     title = {{Ukemi-SafeFall}: An Ukemi-inspired Injury-Aware Falling and Recovery},
     author = {Tran, Anh Duc and Vu, Anh-Quang and Pham, Loc and Nguyen, Trong Hieu and Le, Chuong Nguyen and Dao, Quang Huy and Dao, Hoang Vu and Nguyen, Van-Truong and Nguyen, Chuong and Le, Pham Tuyen and Nguyen, Quan},
     booktitle = {IEEE-RAS International Conference on Humanoid Robots (Humanoids)},
     year = {2026},
     note = {Accepted.}
   }

2025

1. CSF

   

   H∞ tracking control for perturbed discrete-time systems using On/Off policy Q-learning algorithms

   Phuong Nam Dao and Quang Huy Dao

   Chaos, Solitons & Fractals, 2025

   Abs DOI HTML

   The widely studied H∞ zero-sum game problem guarantees the integration of external disturbance into the optimal control problem. In this article, two model-free Q-learning algorithms based on H∞ tracking control are proposed for perturbed discrete-time systems in the presence of external disturbance. Moreover, modification of the output optimal control problem is also made. For the optimal tracking control problem, the existence of a discount factor is necessary to guarantee the final value of the cost function, and the Ricatti equation is modified. With the aid of the deviation between Q functions at two consecutive times and the original principle of Off/On policy, the consideration of H∞ zero-sum game problem, two On/Off Q-learning algorithms based on H∞ tracking control are proposed. Then, by computing the Q function, the influence of probing noise on the Q function is considered. The analysis of solution equivalence proves that convergence and tracking are guaranteed in the proposed algorithm. Eventually, simulation studies are carried out on F-16 aircraft to assess the validity of the presented control schemes.

under review

1. Under review

   

   X-BFM: a Behavioral Foundation Model for Extreme Humanoid Control via World-Model Conditioning and Decoupled Recovery Priors

   Quang Huy Dao et al.

   In IEEE International Conference on Robotics and Automation (ICRA), 2026

   Under review.

   Abs Bib Video Website

   A behavioral foundation model for extreme humanoid control. World-model conditioning and decoupled recovery priors support teleoperation, dynamic skills such as flips, and getting back up, including when the robot is disturbed during recovery.

   @inproceedings{dao2026xbfm,
     title = {{X-BFM}: a Behavioral Foundation Model for Extreme Humanoid Control via World-Model Conditioning and Decoupled Recovery Priors},
     author = {Dao, Quang Huy},
     booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
     year = {2026},
     note = {Under review.}
   }

1. Under review

   

   A model free approach for continuous-time optimal tracking control with unknown user-define cost and constrained control input via advantage function

   Duc Cuong Nguyen, Quang Huy Dao, and Phuong Nam Dao

   Aerospace Science and Technology, 2025

   Under review.

   Abs arXiv Code

   Off-policy continuous-time Q-learning for linear quadratic regulation and tracking with constrained inputs. An advantage function for linear continuous-time systems removes the need to know the reward weights, reset the state, or start from an admissible controller, and does not require the system model. Simulations on an F-16 aircraft.

2. Under review

   Stochastic Integral Reinforcement Learning for Distributed H∞ Optimal Formation Tracking of Multi-Agent Wheeled Mobile Robots

   Khanh Thai, Quang Huy Dao, and Nga Thi-Thuy Vu

   International Journal of Robust and Nonlinear Control, 2026

   Under review.

   Abs Project page

   Distributed H∞ optimal formation tracking for teams of wheeled mobile robots, using stochastic integral reinforcement learning. With Khanh Thai and Nga Thi-Thuy Vu.

preprints

1. 

   iterative Discrete-time High-order Control Barrier Function in Dynamic Environment.

   Bachelor’s Thesis, Hanoi University of Science and Technology, 2025

   Code

2. 

   Zero-Shot Linear Quadratic Regulation from Reward-Free Data: Structured Successor Features with Stability and Finite-Sample Guarantees

   Quang Huy Dao and Khanh Thai

   2026

   Abs Website

   One reward-free dataset is enough for every linear-quadratic task. Structured successor features give a closed-form readout, with stability and finite-sample guarantees, and no second pass over the data.

3. 

   Model-Based and Off-Policy Data-Driven Inverse Reinforcement Learning for Linear Discrete-Time Two-Player Zero-Sum Games via Output Feedback

   Quang Huy Dao, Quoc Dat Lai, and Phuong Nam Dao

   Preprint, 2026

   Abs Website

   Inverse reinforcement learning for linear discrete-time two-player zero-sum games under output feedback, with unknown dynamics. A model-based inverse policy iteration recovers an equivalent output-reward weight by imitating an expert. A model-free off-policy algorithm then uses only the expert’s input-output-disturbance data. Simulations on an F-16 show the learner tracking the expert and meeting the designed disturbance attenuation.

short papers & reports

2023

1. ICCAIS

   Trung Thanh Cao, Quang Huy Dao, and Phuong Nam Dao

   In Q-Learning Algorithm for F16 Aircraft: An approach to Discrete-Time Systems, 2023

   DOI