Mengdi Xu

I am a third-year Ph. D. student advised by Prof. Ding Zhao (SafeAI lab) at Carnegie Mellon University. My research interests lie at the interface of reinforcement learning, cognitive science and robotics. I am passionate about improving robots' robustness and adaptivity, especially in human-in-the-loop multi-agent systems.

Before joining CMU, I received my Master degree in Robotics from LCSR at Johns Hopkins University, supervised by Prof. Gregory S. Chirikjian. I received my Bachelor of Engineering from the School of Vehicle and Mobility and Bachelor of Management from the School of Economics and Management at Tsinghua University.

Email  /  CV  /  Google Scholar  /  Github

profile photo

Research


hpp Accelerated Policy Evaluation: Learning Adversarial Environments with Adaptive Importance Sampling
Mengdi Xu, Peide Huang, Fengpei Li, Jiacheng Zhu, Xuewei Qi, Kentaro Oguchi, Zhiyuan Huang, Henry Lam, Ding Zhao
Preprint, under review
Paper / bibtex
Abridged in ICLR 2021 Workshop in Security and Safety in Machine Learning Systems. Workshop / Poster
hpp Functional Optimal Transport: Map Estimation and Domain Adaptation for Functional data
Jiacheng Zhu, Aritra Guha, Mengdi Xu, Yingchen Ma, Rayleigh Lei, Vincenzo Loffredo, XuanLong Nguyen, Ding Zhao
Preprint, under review
Paper / Code / bibtex
hpp Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
Baiming Chen, Zuxin Liu, Jiacheng Zhu, Mengdi Xu, Wenhao Ding, Liang Li, Ding Zhao
2021 IEEE International Conference on Robotics and Automation (ICRA)
Paper / bibtex
hpp Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen and Ding Zhao
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020
NeurIPS2020 / Arxiv / Code / bibtex
hpp Delay-Aware Multi-Agent Reinforcement Learning
Baiming Chen, Mengdi Xu, Zuxin Liu, Liang Li and Ding Zhao
Preprint, under review
Paper / Code / bibtex
hpp Delay-Aware Model-Based Reinforcement Learning for Continuous Control
Baiming Chen, Mengdi Xu, Liang Li and Ding Zhao
Neurocomputing, 2021
Paper / Code / bibtex
hpp CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios
Wenhao Ding, Mengdi Xu and Ding Zhao
International Conference on Robotics and Automation (ICRA), 2020
Paper / Code / bibtex
hpp Mosquito staging apparatus for producing PfSPZ malaria vaccines
Mengdi Xu, Shengnan Lyu, Yingtian Xu, Can Kocabalkanli, Brian K. Chirikjian, John S. Chirikjian, Joshua Davis, Jin Seob Kim, Iulian Iordachita, Prof. Russell H. Taylor and Gregory S. Chirikjian
IEEE 15th International Conference on Automation Science and Engineering (CASE), 2019
Paper / bibtex
hpp Multi-Mosquito Object Detection and 2D Pose Estimation for Automation of PfSPZ Malaria Vaccine Production
Hongtao Wu, Jiteng Mu, Ting Da, Mengdi Xu, Prof. Russell H. Taylor, Iulian Iordachita and Gregory S. Chirikjian
IEEE 15th International Conference on Automation Science and Engineering (CASE), 2019
Paper / bibtex
hpp Recovering a Rotation Matrix From Three Direction Cosines
Mengdi Xu and Gregory S. Chirikjian
ASME 2018 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC-CIE), 2018
Paper / bibtex
hpp Influence of hydrodynamic pressure and vein strength on the super-elasticity of honeybee wings
Jieliang Zhao*, Mengdi Xu* Youjian Liang, Shaoze Yan and Wendong Niu
Journal of insect physiology, 2018
Paper / bibtex

Experience


  • Assistant to Associate Chief Editor, Robotica, 2018.9-2019.5
  • Teaching Assistant of EN.530.645 Kinematics, Johns Hopkins University, 2018 Fall
  • Teaching Assistant of EN.530.646 Robot Devices, Kinematics, Dynamics, and Control, Johns Hopkins University, 2019 Spring
  • Side Fun Projects


  • Autonomous Quality Inspection System
  • UR5 Maze Solver