Chaoyi Pan

Github 👨‍🎓Scholar Twitter LinkedIn 📮Email

🤖

Welcome to my website!

I am a 3rd-year PhD candidate in Electrical and Computer Engineering affiliated with Robotics Institution at Carnegie Mellon University, working with Prof. Guanya Shi (LeCAR Lab) and Prof. Guannan Qu.

My research interests lie at the intersection of physics-based robot data generation and the understanding of generative models in control.

🗞️News

🎉 [Dec 3rd] “Much Ado About Nosing” is released! The first large-scale empirical study answering the question: "Is there really a benefit to using GCPs for behavior cloning, or are their claimed successes ... much ado about noising?"”

🎉 [Nov 22nd] SPIDER is released! Check it out if you are interested in cross embodiment data generation and learning from human!

🎉 [April 24th 2025] DIAL-MPC made it to the ICRA 2025 Best Paper Award finalist list!

🎉 [Feb 15th 2025] Received the Hsu Chang Memorial Fellowship. Thank you CMU for the recognition!

🎉 [Nov 26th 2024] I passed my PhD qualification exam and am officially a PhD candidate now! 😄

📓Publications

pub-database

notion image

Much Ado About Nosing: Dispelling the Myths of Generative Robotic Control

Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang, Claire Jin, Daniel Pfrommer, Chenyang Yuan, Frank Permenter, Guannan Qu, Nicholas Boffi, Guanya Shi, Max Simchowitz

behavior-cloning

notion image

SPIDER: Scalable Physics-Informed Dexterous Retargeting

Chaoyi Pan, Changhao Wang, Haozhi Qi, Zixi Liu, Homanga Bharadhwaj, Akash Sharma, Tingfan Wu, Guanya Shi, Jitendra Malik, Francois Hogan

learning-from-human

DIAL-MPC is a sampling-based MPC framework with a novel diffusion-style annealing process.

Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing

Haoru Xue*, Chaoyi Pan*, Zeji Yi, Guannan Qu, Guanya Shi

ICRA 2025 [Best paper finalist]

Model-based Diffusion enables flexible trajectory generation without any data.

Model-based Diffusion for Trajectory Optimization

Chaoyi Pan*, Zeji Yi*, Guanya Shi, Guannan Qu

drive.google.com

CoVO-MPC deployed to Crazyflie trajectory long exposure photo.

CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design

Zeji Yi*, Chaoyi Pan*, Guanqi He, Guannan Qu, Guanya Shi

drive.google.com

notion image

In-Hand Manipulation of Unknown Shapes with Tactile Sensing

Chaoyi Pan*, Marion Lepert*, Shenli Yuan, Rika Antonova, Jeannette Bohg

notion image

Efficient Bimanual Handover and Rearrangement via Symmetry-Aware Actor-Critic Learning

Yunfei Li*, Chaoyi Pan*, Huazhe Xu, Xiaolong Wang, Yi Wu

ICRA2023_Bimanual_Rearrange.pdf

notion image

Flexible Decentralized Displacement-Based Formation Control: An Multi-agent Reinforcement Learning Approach

Chaoyi Pan, Yuzi Yan, Zexu Zhang, Yuan Shen

ieeexplore.ieee.org

* indicates co-author.