Wenhao Ding


Wenhao Ding

丁文浩


Ph.D. Candidate, Department of Mechanical Engineering, Carnegie Mellon University.

M.S., Machine Leaning Department, Carnegie Mellon University.

Github / Google Scholar / LinkedIn / CV / Email

I am a third-year Ph.D. student advised by Prof. Ding Zhao of Safe AI Lab. I am also co-advised by Prof. Bo Li of Secure Learning Lab. I received my Bachelor degree from Electronic Engineering, Tsinghua University.

I am an FPV drone flyer. Check my gallery.

Research Highlights

My research goal is to build robust, generalizable, and interpretable autonomous systems that can truly understand the physical world. Specifically, I am interested in the following topics:

  • Adversarial Machine Learning. Improving robustness by training against semantic adversarial examples.
  • Zero-shot Generalization. Generalizating algorithms to unseen tasks by extracting structured features.
  • Causal Reinforcement Learning. Making generalizable decisions by discovering the underlying causality.

    • News & Updates

    2022/04 - We got into the Finalist of 2022 Qualcomm Innovation Fellowship.

    2022/03 - I will start my Applied Scientist Intern in Amazon Lab126 working on Astro.

    2022/02 - I gave a talk about scenario generation in Upenn hosted by Prof. Rahul Mangharam.

    2022/01 - We are holding the Season Depth Challenge in IROS 2022 and ICRA 2022.

    2022/01 - I gave a talk about scenario generation in Stanford SISL Lab.

    Selected Publications

    Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

    Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
    Preprint arXiv:2207.09081

    arXiv / code / bibtex

    SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles

    *Chejian Xu, *Wenhao Ding, Weijie Lyu, Zuxin Liu, Shuai Wang, Yihan He, Hanjiang Hu, Ding Zhao, Bo Li
    Preprint arXiv:2206.09682

    arXiv / code / bibtex

    A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective

    Wenhao Ding, Chejian Xu, Mansur Arief, Haohong Lin, Bo Li, Ding Zhao
    Preprint arXiv:2202.02215

    arXiv / code / bibtex

    CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation

    Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
    ICML 2022 Workshop on Safe Learning for Autonomous Driving

    arXiv / code / bibtex

    Semantically Adversarial Driving Scenario Generation with Explicit Knowledge Integration

    Wenhao Ding, Haohong Lin, Bo Li, Kim Ji Eun, Ding Zhao
    Preprint arXiv:2106.04066

    arXiv / code / bibtex

    Certifiable Deep Importance Sampling for Rare-Event Simulation of Black-Box Systems

    Mansur Arief, Yuanlu Bai, Wenhao Ding, Shengyi He, Zhiyuan Huang, Henry Lam, Ding Zhao
    Preprint arXiv:2111.02204

    arXiv / code / bibtex

    Context-Aware Safe Reinforcement Learning for Non-Stationary Environments

    Baiming Chen, Zuxin Liu, Jiacheng Zhu, Mengdi Xu, Wenhao Ding, Liang Li, Ding Zhao
    IEEE International Conference on Robotics and Automation (ICRA) 2021

    arXiv / code / bibtex

    Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

    Wenhao Ding, Baiming Chen, Bo Li, Kim Ji Eun, Ding Zhao
    IEEE Robotics and Automation Letters (and ICRA 2021)

    arXiv / code / bibtex

    Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

    Mengdi Xu, Wenhao Ding, Jiacheng Zhu, Zuxin Liu, Baiming Chen, Ding Zhao
    Neural Information Processing Systems (NeurIPS) 2020, Vancouver

    arXiv / code / bibtex

    Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method

    Wenhao Ding, Baiming Chen, Minjun Xu, Ding Zhao
    International Conference on Intelligent Robots and Systems (IROS) 2020, Las Vegas

    arXiv / code / video / bibtex

    CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarios

    Wenhao Ding, Mengdi Xu, Ding Zhao
    International Conference on Robotics and Automation (ICRA) 2020, Paris

    arXiv / code / supplementary / bibtex

    A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters

    Wenhao Ding, Wenshuo Wang, Ding Zhao
    International Conference on Robotics and Automation (ICRA) 2019, Montreal

    arXiv / code / supplementary / bibtex

    Academic Services

    Conference Reviewer: ICML, ICLR, NeurIPS, CVPR, ECCV, ICCV, ICRA, IROS, ICME

    Journal Reviewer: TMLR, IEEE RA-L, IEEE Access, IEEE T-ITS, IEEE TII, IEEE MM

    Organizer: ICRA 2022 SeasonDepth Challenge

     

    Updated on July 22nd, 2022

                   
    Wenhao Ding © 2018-2022