Xinyi Yu

My name is Xinyi Yu (pronunciation). I am a PhD student in Computer Science at University of Southern California (USC) advised by Prof. Gaurav S. Sukhatme in the USC Robotic Embedded Systems Laboratory (RESL). I received the M.S. degree in Control Science and Engineering from Shanghai Jiao Tong University (SJTU), advised by Prof. Shaoyuan Li and Prof. Xiang Yin in 2023, and the B.S. degree in Department of Automation from China University of Petroleum, East China (UPC) in 2020.

My research interests center on robotics, and I am broadly interested in leveraging diverse technologies to make robots work in the real world. Currently, I focus on robotic manipulation, especially large-object upper-body manipulation. My earlier work focused on the theory of control, optimization, and verification, with applications in task and motion planning.

Email: xinyi.yu12@usc.edu | GitHub | Google Scholar | LinkedIn

Eat well, sleep well, and keep smiling!

Selected Publications

(* indicates equal contribution, see full list on Google Scholar)

Manipulation

ARMFUL: Learning Whole-Arm Grasp Configurations for Single-Arm Pickup of Large Objects
Xinyi Yu, Yunshuang Li, Daniel Seita, Gaurav S. Sukhatme
submitted, 2026 [arXiv (coming soon)][project page][code (coming soon)]
BiREPO: Learning Goal-Conditioned Bimanual Nonprehensile Pose Reconfiguration Primitives on Diverse Objects
Yunshuang Li*, Xinyi Yu*, Jason Chen*, Changyang Zhang, Faiz Aladin, Gaurav S. Sukhatme, Daniel Seita
submitted, 2026 [arXiv (coming soon)][project page][code (coming soon)]

Control, Optimization, and Verification

Conformal Predictive Programming for Chance Constrained Optimization
Conformal Predictive Programming for Chance Constrained Optimization
Yiqi Zhao*, Xinyi Yu*, Matteo Sesia, Jyotirmoy V. Deshmukh, Lars Lindemann
submitted, 2026 [arXiv][code]
Signal Temporal Logic Control Synthesis among Uncontrollable Dynamic Agents with Conformal Prediction
Signal Temporal Logic Control Synthesis among Uncontrollable Dynamic Agents with Conformal Prediction
Xinyi Yu, Yiqi Zhao, Xiang Yin, Lars Lindemann
Automatica (Regular paper), 2026 [arXiv][code]
Sleep When Everything Looks Fine: Self-Triggered Monitoring for Signal Temporal Logic Tasks
Sleep When Everything Looks Fine: Self-Triggered Monitoring for Signal Temporal Logic Tasks
Chuwei Wang, Xinyi Yu, Jianing Zhao, Lars Lindemann, Xiang Yin
IEEE Robotics and Automation Letters (RA-L), 2024 [arXiv][code]
Model Predictive Monitoring of Dynamical Systems for Signal Temporal Logic Specifications
Model Predictive Monitoring of Dynamical Systems for Signal Temporal Logic Specifications
Xinyi Yu, Weijie Dong, Shaoyuan Li, Xiang Yin
Automatica (Regular paper), 2024 [arXiv][code]
Efficient STL Control Synthesis under Asynchronous Temporal Robustness Constraints
Efficient STL Control Synthesis under Asynchronous Temporal Robustness Constraints
Xinyi Yu, Xiang Yin, Lars Lindemann
IEEE Conference on Decision and Control (CDC), 2023 [arXiv][code]
Model Predictive Control for Signal Temporal Logic Specifications with Time Interval Decomposition
Model Predictive Control for Signal Temporal Logic Specifications with Time Interval Decomposition
Xinyi Yu, Chuwei Wang, Dingran Yuan, Shaoyuan Li, Xiang Yin
IEEE Conference on Decision and Control (CDC), 2023 [arXiv][code]
Online Monitoring of Dynamic Systems for Signal Temporal Logic Specifications with Model Information
Online Monitoring of Dynamic Systems for Signal Temporal Logic Specifications with Model Information
Xinyi Yu, Weijie Dong, Xiang Yin, Shaoyuan Li
IEEE Conference on Decision and Control (CDC), 2022 [arXiv]