Reward-Guided Domain Randomization (RGDR)
A project proposing an adaptive domain-randomization framework that improves robustness and generalization of autonomous-driving RL policies through reward-guided sampling.
View Code on GitHub
Posts by Collection
portfolio
Robust Reinforcement Learning for Autonomous Driving in Uncertain Environments
A history-dependent reinforcement-learning framework that improves policy adaptability and robustness in dynamic, partially observable driving environments using randomized dynamics, context-aware rewards, and LSTM-based policy optimization.
project
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
A fast mixed distributed fusion for systems with random parameter matrices and correlated noises
Published in 41st Chinese Control Conference (CCC), 2022
Adaptive control of 3R manipulator in the workspace based on radial basis function neural network
Published in Chinese Intelligent Systems Conference (CISC), 2022
An order insensitive optimal generalized sequential fusion estimation for stochastic uncertain multi-sensor systems with correlated noise
Published in IET Signal Processing, 2023
Discrete fixed-time observers over sensor networks with unknown noise
Published in Ad Hoc Networks, 2023
Robust event-triggered distributed fusion for multi-sensor systems with unknown failure rates
Published in Journal of the Franklin Institute, 2023
RGDR: Reward-Guided Domain Randomization for Autonomous Driving
Published in IEEE Intelligent Transportation Systems Conference (ITSC), 2025
Robust Reinforcement Learning for Autonomous Driving in Uncertain Environments
Published in IEEE International Conference on Automation Science and Engineering (CASE), 2025
RGDR: Reward-Guided Domain Randomization for Autonomous Driving (Poster)
Published in Poster presented at the CEE Research Expo, Northeastern University, Boston, MA, 2025
talks
Dragon Boat Paddler
I am a dragon boat paddler. Dragon boat paddling has become a sport that challenges both physical endurance and team coordination. I paddle for Boston Storm Dragon Boat Club as well as Nankaitianda Dragon boat team (南开天大南天门龙舟队). I train regularly with my teammates and participate in dragon boat races. Here are some memorable moments from my journey:
Hiking
I love hiking. Hiking has become one of the most refreshing and grounding parts of my routine in autumn, when I explore mountain trails, lakeside routes, and forest paths to enjoy the vibrant foliage across New England. Below are some of the moments from my hikes:
Badminton Holic
I am a badminton holic. Outside my academic and research life, badminton has become one of the most important parts of my routine. I regularly play singles and doubles. I have been playing badminton for three years, and I also participate in badminton competitions. These are some of the medals I have earned:
teaching
Teaching Assistant – Undergraduate Physics Laboratory
Undergraduate course, Nankai University, School of Physics, 2023
As a Teaching Assistant for undergraduate physics laboratory courses, I provided instructional and academic support to enhance students’ understanding of experimental methods and data-driven reasoning.
Teaching Assistant – Probability and Engineering Economy for Civil Engineering
Undergraduate course, Northeastern University, College of Engineering, 2026
As a Teaching Assistant for Probability and Engineering Economy courses in Civil Engineering, I provided instructional and academic support to enhance students’ understanding of Probability Theory.