Chaoyi Pan

Chaoyi Pan

PhD Candidate, Carnegie Mellon University

I am a 3rd-year PhD candidate in Electrical and Computer Engineering affiliated with the Robotics Institute 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

Publications

* denotes equal contribution.

Action Representation in Generative Control

Much Ado About Noising teaser

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

Chaoyi Pan, Gokul Anantharaman, Nicholas Huang, Chris Jin, Daniel Pfrommer, Chengyi Yuan, Frank Permenter, Guannan Qu, Nicolò Boffi, Guanya Shi, Max Simchowitz

ICLR 2026

Physics-based Data Generation

SPIDER teaser

SPIDER: Scalable Physics-Informed Dexterous Retargeting

Chaoyi Pan, Chaoqiang Wang, Hao Qi, Zhiao Liu, Harish Bharadhwaj, Abhinandan Sharma, Taosha Wu, Guanya Shi, Jitendra Malik, Frank Hogan

arXiv 2025

Model-based Diffusion teaser

Model-Based Diffusion for Trajectory Optimization

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

NeurIPS 2024

Sampling-based Optimization

DIAL-MPC teaser

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

CoVO-MPC teaser

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

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

L4DC 2024

Robotics Systems

In-Hand Manipulation teaser

In-Hand Manipulation of Unknown Shapes with Tactile Sensing

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

IROS 2023

Bimanual Handover teaser

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

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

ICRA 2023

Formation Control teaser

Flexible Decentralized Displacement-Based Formation Control: A Multi-Agent Reinforcement Learning Approach

Chaoyi Pan, Yuzi Yan, Zexu Zhang, Yuan Shen

EUSIPCO 2022

Blog

View All Posts →

Projects

Agile Drone Transportation

Agile Drone Transportation with Explicit Time Trajectory Optimization

Trajectory optimization for quadrotor drones carrying slung payloads, enabling aggressive aerial transportation maneuvers through explicit time optimization and collision-aware planning.

Blind Navigation Headgear

Intelligent Blind Navigation Headgear Based on Head Conditioned Reflexes

A wearable headgear system that guides visually impaired users through head-conditioned reflex signals for intuitive, hands-free obstacle avoidance navigation.

Experience

Jan 2026 – Present

Amazon Frontier AI and Robotics Lab

Research Intern · San Francisco, USA

Working on understanding of action representation and large-scale behavior cloning data collection. Supervised by Prof. Guanya Shi and Prof. Rocky Duan.

Jun – Aug 2025

Meta FAIR Embodiment & Actions Research Team

Research Science Intern · Pittsburgh, USA

Developed universal human-to-robot physics-based retargeting system for converting raw human interaction trajectories to feasible robot trajectories. Supervised by Francois Hogan.

Jun 2023 – Present

Carnegie Mellon University

PhD Student · Pittsburgh, USA

Developing generative models for control, bridging learning-based generative models with model-based control for contact-rich real-world tasks. Supervised by Prof. Guanya Shi and Prof. Guannan Qu.

Jun – Sep 2022

Stanford Interactive Perception and Robot Learning Lab

Summer Intern · Stanford, USA

Implemented tactile-based in-hand manipulation system using Bayesian optimization without object shape prior or vision information. Supervised by Prof. Jeannette Bohg.

Sep 2021 – Jun 2022

Tsinghua WuLab

Research Assistant · Beijing, China

Developed bimanual coordination system for handover and rearrangement tasks using structured reinforcement learning. Supervised by Prof. Yi Wu.

Oct 2020 – Sep 2021

Tsinghua SLab

Research Assistant · Beijing, China

Designed decentralized formation control system for mobile robots using multi-agent RL and Hausdorff distance. Supervised by Prof. Yuan Shen.