Boshi An | 安博施

Email  /  Google Scholar  /  Github  /  Linkedin  /  WeChat

Introduction

I received honours degree (summa cum laude) from Turing class at the School of Computer Science, Peking University. At Peking University, I was mainly advised by Prof. Hao Dong on robotics learning. I also collaborated closely with Prof. Zongqing Lu on the spatial cognitive abilities of machine learning models.

profile photo
Research

I'm interested in reinforcement learning, robotics and computational neurology.





MyoChallenge: Die reorientation
Boshi An, Yiran Geng, 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.




End-to-End Affordance Learning for Robotic Manipulation

Yiran Geng*, Boshi An*, Haoran Geng, Yuanpei Chen, Yaodong Yang, Hao Dong
ArXiv / Project Page / Code
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.




Learning Multi-object Positional Relations via Emergent Communication

Yicheng Feng*, Boshi An*, Zongqing Lu
ArXiv / Project Page (Coming Soon) / Code (Coming Soon)
AAAI 2024 Oral

We investigated whether a compositional language for describing 2-D positional relation can emerge from communication under environmental pressure.




RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation

Boshi An*, Yiran Geng*, Kai Chen*, Xiaoqi Li, Qi Dou, Hao Dong
ArXiv / Project Page / Code
ICRA 2024

We achieved state-of-the-art manipulation performance by combining reinforcement learning and multi-view pose estimation.




Bilateral Propagation Network for Depth Completion

Jie Tang, Fei-Peng Tian, Boshi An, Jian Li, Ping Tan
ArXiv / Project Demo / Code
CVPR 2024

We proposed an image-guided depth completion model which is SOTA on NYUv2 dataset and won the first place on KITTY benchmark at the time of submission.

Preprints



ImageManip Image-based Robotic Manipulation with Affordance-guided Next View Selection

Xiaoqi Li, Yanzi Wang, Yan Zhao, Yaroslav Ponomarenko, Qianxu Wang, Haoran Lu, Boshi An, Jiaming Liu, Hao Dong
ArXiv / Project Page (Coming Soon) / Code (Coming Soon)

We propose a framework that utilizes only RGB inputs and enables 3D articulated object manipulation.

Experience
Turing Class, Peking University, China
2020.09 - 2024.07
Undergraduate Student, Summa cum laude
Research Advisor: Prof. Hao Dong
Adaptive Motor Control Lab, EPFL, Switzerland
2023.07 - 2023.08
Research Intern
Research Advisor: Prof. Alexander Mathis
University of Edinburgh, United Kingdom
2023.09 - 2023.12
Exchange Student


Selected Awards and Honors

  • 2024: Honours Degree in Science
  • 2024: Outstanding Graduates Prize (Peking University)
  • 2023: Distinguished Researcher Prize (Peking University)
  • 2022: First Place in NeurIPS 2022 Challenge Track 🏅
  • 2022: John Hopcroft Scholarship
  • 2020: Outstanding Freshman Scholarship
  • 2019: Chinese Olympiad in Informatics (NOI) Gold Medalist and National Training Team member 🏅

  • Misc

    I am a piano player interested in classical music, especially chamber music, you can find my recordings in my Bilibili page .


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