Qingquan Bao

Qingquan Bao /tɕʰɪŋ/ /tɕʰɥœn/ /bɑʊ/

M.S. in Robotics 25'

University of Pennsylvania

Biography

Hello! I’m Qingquan Bao, currently a graduate student specializing in robotics at the General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania. I’m on the lookout for internship opportunities in Machine Learning Engineering or Software Engineering. Please feel free to get in touch!

My aspiration is to develop a versatile agent capable of assisting with both physical and intellectual tasks in our daily lives. I firmly believe that embodied AGI is crucial for advancing humanity liberty and democracy. So my current research interests focous on robot learning (esp. in mobile manipulation task), LLM in planning and RAG. Professionally, I am keen on implementing intelligent systems in cyberspace or ACTUAL robotic applications.!

Prior to joining Penn, I graduated cum laude (Zhiyuan Honor) in 2023 from Shanghai Jiao Tong University. During my enriching undergraduate years, I collaborated with Professor Junchi Yan on topics of Vision Graph Matching, Trustworthy AI, and Neural Architecture Search. I also had the privilege of working with Professors Joshua B. Tenenbaum, Chuang Gan, Leslie Pack Kaelbling, Tomás Lozano-Pérez in the field of Embodied AI.

Interests
  • Artificial General Intelligence
  • Robotics and Embodied AI
  • Humanoid Robots
  • Mobile Manipulation
Education
  • M.S. in Robotics, 2025 (Expected)

    University of Pennsylvania

  • B.E. in Artificial Intelligence, 2023

    Shanghai Jiao Tong Univerisity

Skills

Technical
Python
Deep Learning (Pytorch)
SQL
Hobbies
tennis Tennis
Photography
sword Kendo

Experience

 
 
 
 
 
Research Assitant
July 2022 – January 2023 Cambridge, MA, US
Led the research project “Embodied Depth Prediction”
 
 
 
 
 
Shanghai Jiao Tong University
Research Assitant
Shanghai Jiao Tong University
December 2020 – June 2023 Shanghai, China

Projects include:

  • Deep Graph Matching library with PaddlePaddle
  • Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and Beyond
  • Visual Model Search and Optimization for Software and Hardware Co-design (My Bachelor’s thesis)

Projects

*
Embodied Depth Prediction
We study the problem of embodied depth prediction, where an embodied agent in an environment must learn to accurately estimate the depth of its surroundings.
Embodied Depth Prediction
Heuristic Reward Driven Athlete Trainer
Let’s train an excellent Olymic runner with partial observations and use curiosity as dense rewards!
Heuristic Reward Driven Athlete Trainer
Deep Graph Matching library with PaddlePaddle
Contribute to an over 700⭐️ open-source graph matching model library!
Deep Graph Matching library with PaddlePaddle

Contact

Feel free to contact me!