Yaru Niu

yaru.jpg

yarun@andrew.cmu.edu

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.

CV /  Google Scholar /  Twitter /  Github /  Linkedin

News

Nov, 2023 Our work RoboTool is covered by TechXplore.
Jul, 2023 We release the report of RoboDepth (Robust Out-of-distribution Depth prediction) Challenge at ICRA 2023. The event recording is available here.
Jun, 2023 Our work on goal-conditioned curriculum reinforcement leanring for robotic scooping is accepted to IROS 2023.
Jan, 2023 Our work on group distributionally robust reinforcement learning is accepted to AISTATS 2023.
Jun, 2022 Our work on interactive motion prediction for autonomous driving is accepted to IROS 2022.
May, 2022 I graduate from Georgia Tech. Thank you, GT. Check out my MS Thesis.
Apr, 2022 I will join Safe AI Lab at CMU as a PhD student starting from Fall 2022.
Apr, 2022 Our work Interpretable Continuous Control Tree (ICCT) is accepted to RSS 2022!
Oct, 2021 Our work Multi-Agent Graph-Attention Communication (MAGIC) receives the Best Paper Award at ICCV 2021 Mair2 Workshop!
Dec, 2020 Our paper on multi-agent reinforcement learning (MAGIC) is accepted to AAMAS 2021 for oral presentation!

Selected Publications

Notation * indicates equal contributions.

  1. Creative Robot Tool Use with Large Language Models
    Mengdi Xu*, Peide Huang*, Wenhao Yu, Shiqi Liu, Xilun Zhang,  Yaru Niu, Tingnan Zhang, Fei Xia, Jie Tan, Ding Zhao
    arXiv preprint, 2023
    Abridged in CoRL 2023 Workshop on Language and Robot Learning (LangRob): Language as Grounding
    PDF Webpage Media (TechXplore) Media (中文)
  2. Safety-aware Causal Representation for Trustworthy Reinforcement Learning in Autonomous Driving
    Haohong Lin, Wenhao Ding, Zuxin Liu,  Yaru Niu, Jiacheng Zhu, Yuming Niu, Ding Zhao
    arXiv preprint, 2023
    Abridged in Machine Learning for Autonomous Driving Symposium
    PDF Webpage
  3. GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning
    Yaru Niu, Shiyu Jin*, Zeqing Zhang*, Jiacheng Zhu, Ding Zhao, Liangjun Zhang
    In International Conference on Intelligent Robots and Systems (IROS), 2023
    Abridged in ICRA 2023 Workshop on Representing and Manipulating Deformable Objects [PDF] [Spotlight Talk]
    PDF Webpage Talk Video
  4. COMPOSER: Scalable and Robust Modular Policies for Snake Robots
    Yuyou Zhang,  Yaru Niu, Xingyu Liu, Ding Zhao
    arXiv preprint, 2023
    Abridged in CoRL 2023 Workshop on Learning for Soft Robots: Hard Challenges for Soft Systems (Spotlight)
    PDF Webpage
  5. Interpretable Reinforcement Learning for Robotics and Continuous Control
    Rohan Paleja*, Letian Chen*,  Yaru Niu*, Andrew Silva, Zhaoxin Li, Songan Zhang, Chace Ritchie, Sugju Choi, Kimberlee Chestnut Chang, Hongtei Eric Tseng, Yan Wang, Subramanya Nageshrao, Matthew Gombolay
    arXiv preprint, 2023
    PDF Code
  6. Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables
    Mengdi Xu, Peide Huang,  Yaru Niu, Visak Kumar, Jielin Qiu, Chao Fang, Kuan-Hui Lee, Xuewei Qi, Henry Lam, Bo Li, Ding Zhao
    In International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
    Also appeared in 5th Symposium on Advances in Approximate Bayesian Inference
    PDF Webpage
  7. Domain Knowledge Driven Pseudo Labels for Interpretable Goal-Conditioned Interactive Trajectory Prediction
    Lingfeng Sun*, Chen Tang*,  Yaru Niu, Enna Sachdeva, Chiho Choi, Teruhisa Misu, Masayoshi Tomizuka, Wei Zhan
    In International Conference on Intelligent Robots and Systems (IROS), 2022
    PDF Slides Talk
  8. Adaptable and Scalable Multi-Agent Graph-Attention Communication
    Yaru Niu
    Committee:  Matthew Gombolay,  Ayanna Howard,  Sonia Chernova
    Master’s Thesis, Georgia Institute of Technology, 2022
    HTML PDF
  9. Learning Interpretable, High-Performing Policies for Autonomous Driving
    Rohan Paleja*,  Yaru Niu*, Andrew Silva, Chace Ritchie, Sugju Choi, Matthew Gombolay
    In Robotics: Science and Systems (RSS), 2022
    HTML PDF Code Talk
  10. Multi-Agent Graph-Attention Communication and Teaming
    Yaru Niu*, Rohan Paleja*, Matthew Gombolay
    In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021 (Oral)
    Best Paper Award at ICCV 2021 Mair2 Workshop [PDF] [Spotlight Talk]
    PDF Code Talk
  11. Real-Time Whole-Body Imitation by Humanoid Robots and Task-Oriented Teleoperation using an Analytical Mapping Method and Quantitative Evaluation
    Zhijun Zhang*,  Yaru Niu*, Ziyi Yan, Shuyang Lin
    Applied Sciences, 2018
    HTML PDF Code Video