5000 Forbes Avenue
Pittsburgh, PA 15213
Hi! I am a second-year PhD candidate at CMU Safe AI Lab, advised by Prof. Ding Zhao. Previously, I received an M.S. in Electrical and Computer Engineering at Georgia Tech, working with Prof. Matthew Gombolay. Before that, I received a B.E. in Intelligence Science and Technology at South China University of Technology. I also spent wonderful time as a research intern at Baidu Research with Dr. Liangjun Zhang, and at Berkeley with Prof. Masayoshi Tomizuka.
My research interest lies at the intersection of robotics, machine learning, and multi-agent systems. My research goal is to build methodologies for collaborative, interpretable, and reliable intelligent robotic systems that can interact with complex environments around them.
My Chinese name is 牛雅儒 (Niu-Ya-Ru), where my first name (雅儒) means a scholar with elegance in ancient Chinese.
Notation * indicates equal contributions.
Creative Robot Tool Use with Large Language ModelsarXiv preprint, 2023
Abridged in CoRL 2023 Workshop on Language and Robot Learning (LangRob): Language as Grounding
Safety-aware Causal Representation for Trustworthy Reinforcement Learning in Autonomous DrivingarXiv preprint, 2023
Abridged in Machine Learning for Autonomous Driving Symposium
GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement LearningIn International Conference on Intelligent Robots and Systems (IROS), 2023
Abridged in ICRA 2023 Workshop on Representing and Manipulating Deformable Objects [PDF] [Spotlight Talk]
COMPOSER: Scalable and Robust Modular Policies for Snake RobotsarXiv preprint, 2023
Abridged in CoRL 2023 Workshop on Learning for Soft Robots: Hard Challenges for Soft Systems (Spotlight)
Interpretable Reinforcement Learning for Robotics and Continuous ControlarXiv preprint, 2023
Group Distributionally Robust Reinforcement Learning with Hierarchical Latent VariablesIn International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Also appeared in 5th Symposium on Advances in Approximate Bayesian Inference
Domain Knowledge Driven Pseudo Labels for Interpretable Goal-Conditioned Interactive Trajectory PredictionIn International Conference on Intelligent Robots and Systems (IROS), 2022
Adaptable and Scalable Multi-Agent Graph-Attention CommunicationMaster’s Thesis, Georgia Institute of Technology, 2022
Learning Interpretable, High-Performing Policies for Autonomous DrivingIn Robotics: Science and Systems (RSS), 2022
Real-Time Whole-Body Imitation by Humanoid Robots and Task-Oriented Teleoperation using an Analytical Mapping Method and Quantitative EvaluationApplied Sciences, 2018