Yiran Geng | 耿逸然

I am a junior student in Turing class at the School of Computer Science, Peking University and a research intern at Beijing Institute for General Artificial Intelligence (BIGAI), co-advised by Prof. Hao Dong and Prof. Yaodong Yang.

Email  /  Google Scholar  /  Github /  Twitter /  WeChat

profile photo
Research

My research focuses on robotics, reinforcement learning, and computer vision. My academic goal is to build robotic systems with strong generalization, high stability and safety and to make them real-world implementable.




RLAfford: End-to-End Affordance Learning for Robotic Manipulation

Yiran Geng*, Boshi An*, Haoran Geng, Yuanpei Chen, Yaodong Yang, Hao Dong
ArXiv / Project Page / Video / Media / Code (Coming Soon)
ICRA 2023

In this study, we take advantage of visual affordance by using the contact information generated during the RL training process to predict contact maps of interest.

GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF
Qiyu Dai*, Yan Zhu*, Yiran Geng, Ciyu Ruan, Jiazhao Zhang, He Wang
ArXiv
ICRA 2023

We propose a multiview RGB-based 6-DoF grasp detection network, GraspNeRF, that leverages the generalizable neural radiance field (NeRF) to achieve material-agnostic object grasping in clutter.



GenDexGrasp: Generalizable Dexterous Grasping
Puhao Li*, Tengyu Liu*, Yuyang Li, Yiran Geng, Yixin Zhu, Yaodong Yang, Siyuan Huang
ArXiv / Project Page / Code
ICRA 2023

This paper introduces GenDexGrasp, a versatile dexterous grasping method that can generalize to unseen hands.





MyoChallenge: Die Rotation
Yiran Geng, Boshi An, Yifan Zhong, Jiaming Ji, Yuanpei Chen
Challenge Page / Code / Slides / Talk
First Place in NeurIPS 2022 Challenge Track (1st in 340 submissions from 40 teams)

Reconfiguring a die to match desired goal orientations. This task require delicate coordination of various muscles to manipulate the die without dropping it.



Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Yiran Geng, Hao Dong, Zongqing Lu, Song-chun Zhu, Yaodong Yang
Project Page / ArXiv / Code
NeurIPS 2022

We propose a bimanual dexterous manipulation benchmark (Bi-DexHands) according to literature from cognitive science for comprehensive reinforcement learning research.

Preprints
GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning
Tianhao Wu*, Fangwei Zhong*, Yiran Geng, Yaodong Yang, Yizhou Wang, Hao Dong
ArXiv
Under Review 2023

This study is the first attempt to formulate the dynamic grasping problem as a “move-and-grasp” game and use adversarial RL to train the grasping policy and object moving strategies jointly.

Before 2022


Ministry of Education Talent Program Thesis (Physics Track)
Yiran Geng, Haoran Geng, Xintian Dong, Yue Meng, Xujv Sun, Houpu Niu
PDF
Selected as the Outstanding Thesis of the National Physics Forum 2018

During my high school years, I was selected for the Ministry of Education Talent Program and conducted physics research at Nankai University and presenting my thesis at the National Physics Forum 2018.


Recent Talks

  • I'll give a talk at NeurIPS 2022 MyoChallenge workshop at Dec 7 from 21h to 24h (UTC time).
    Link / Slides
  • I'll give a talk "Agent Manipulation Skill Learning through Reinforcement Learning" at CS Peer Talks at CFCS, Peking University (Time TBD).
    Link
  • I'll give a talk "End-to-End Affordance Learning for Robotic Manipulation" at CFCS Frontier Storm at CFCS, Peking University (Time TBD).
    Link / Poster

  • Services

  • Volunteer: WINE 2020
  • Reviewer: CVPR 2023

  • Teaching Assistant

  • Probability and Statistics (A) (Spring 2023)
  • Frontier Research Practice II (Prof. Hao Dong Track, Spring 2023)

  • Experience

    Turing Class, Peking University, China
    2020.09 - now
    Undergraduate Student
    Research Advisor: Prof. Hao Dong
    Academic Advisor: Prof. Zhenjiang Hu
    Beijing Institute for General Artificial Intelligence (BIGAI) , China
    2022.05 - now
    Research Intern
    Research Advisor: Prof. Yaodong Yang
    Academic Advisor: Prof. Song-Chun Zhu


    Selected Awards and Honors

  • 2022: Beijing Institute for General Artificial Intelligence (BIGAI) Outstanding Contribution Award
  • 2022: Center on Frontiers of Computing Studies (CFCS) Outstanding Student
  • 2022: John Hopcroft Scholarship (3000RMB¥)
  • 2022: First Place in NeurIPS 2022 Challenge Track (3000€) 🏅
  • 2022: Peking University Research Excellence Award
  • 2022: Peking University Dean's Scholarship (15000RMB¥)
  • 2021: SenseTime Scholarship (Youngest winner, 20000RMB¥)
  • 2021: Peking University Study Excellence Award
  • 2021: Peking University Qinjin Scholarship (10000RMB¥)
  • 2021: John Hopcroft Scholarship (3000RMB¥)
  • 2021: Ministry of Education Top Talent Program Scholarship (1000RMB¥)
  • 2019: Chinese Physics Olympiad (CPHO) Gold Medalist 🏅

  • This template is a modification to Jon Barron's website.