Yifei Simon Shao (邵逸飞)
🐭🐭🐭 From Hangzhou, China
GRASP Lab
University of Pennsylvania
Philadelphia, PA
Generalist robots will be around humans before they can be fully autonomous! I want human and robots to collaborate in a way that is efficient, safe, and scalable.
I am a 4th year PhD student at UPenn’s GRASP Lab, developing generalizable, provable and VLM-driven robot systems for long-horizon, real-world physical human robot collaboration. I excel at bringing theory to hardware in quadrotors, mobile manipulators, quadrupeds, and autonomous vehicles. First-author papers in T-RO, RSS, RA-L, and ICRA.
I run a red note account that interviews robotics researchers and shoot live demos of their work. If you’d like more people to see your work, please email me! RedNote.
I am co-advised by Prof. Vijay Kumar and Prof. Pratik Chaudhari. I also work very closely with Prof. Nadia Figueroa.
See my Google Scholar for a complete list of publications.
Click on videos to zoom in!
selected publications
- IROS
Collision Detection for Low-Cost Robot Manipulators Using Probabilistic Residual Torque ModelingIROS, 2025 - CoRL Workshop
Symskill: Symbol and Skill Co-Invention for Data-Efficient and Real-Time Long-Horizon ManipulationarXiv preprint arXiv:2510.01661, 2025 - CoRL Workshop
Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots2025 - RSS
Don’t Yell at Your Robot! Constraint-Aware Intent Estimation for Dynamic Human-Robot Object Co-ManipulationRobotics: Science and Systems, 2024 - T-RO
Refine: Reachability-based trajectory design using robust feedback linearization and zonotopesIEEE Transactions on Robotics, 2024 - ICRA
Design and evaluation of motion planners for quadrotors in environments with varying complexitiesIn 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024 - RA-L
Reachability-based trajectory safeguard (rts): A safe and fast reinforcement learning safety layer for continuous controlIEEE Robotics and Automation Letters, 2021
news
| Oct 24, 2025 | I chaired workshop at IROS 2025: RoboGen: 3D World Generation for Robot Learning and Autonomous Systems. The workshop was a great success. My talk can be found here. |
|---|---|
| Oct 16, 2025 | My paper EgoPartner: VLM Ego-Centric Action Recognition and Cost-Aware Task Allocation for Human Robot Collaboration accepted to IROS 2025 Workshop: Human-in-the-loop Robot Learning in the Era of Foundation Models. |
| Sep 27, 2025 | Won Best Paper Award (5%) at CoRL Learning Effective Abstraction for Planning Workshop 2025 for SymSkill: Low-Data Symbol and Skill Learning |
| Sep 27, 2025 | Oral Presentation (20%) at CoRL RoboArena Workshop 2025 for Maestro: VLM-Based Modular Generalist Robot. Contact me if you want to bring Maestro to your own quadrupedal mobile manipulator! |
| Jun 30, 2025 | Paper on fast collision detection using GMM for manipulators accepted to IROS 2025 |
| Sep 01, 2024 | Started Research Scientist Internship at Amazon Lab126 working on next-generation robotics! |
| Jul 19, 2024 | Paper Constraint-Aware Intent Estimation for Dynamic Human-Robot Object Co-Manipulation accepted to RSS 2024 and Don’t Yell at Your Robot! accepted to RSS GenAI-HRI Workshop 2024 |
| Apr 29, 2024 | Paper on Two Stage Motion Planning accepted to ICRA 2024, making it possible for the first time to choose the best planner for your environment. |
| Feb 16, 2024 | Paper on Safe Motion Planning with Zonotopes accepted to T-RO 2024, making safe motion planning possible even with tracking errors! |
| Sep 01, 2022 | Started PhD at GRASP UPenn coadvised by Prof. Vijay Kumar and Prof. Pratik Chaudhari |