Hantao Ye

I am a second-year Ph.D. student in Electrical and Computer Engineering at the University of Minnesota, Twin Cities, advised by Prof. Changhyun Choi in the Choice Robotics Lab. My research focuses on deformable object manipulation and robot learning. In summer 2026, I was a Robotics Research Intern at GrayMatter Robotics (Carson, CA), where I worked on a world model for robotic sanding.

Before joining UMN, I was a research assistant at RRoS Lab, advised by Prof. SK Gupta, working on robot control and simulation. I graduated with a Master's degree in Computer Science from the University of Southern California in 2024. Prior to that, I received my Bachelor's degree in Mechatronics Engineering from Beijing Jiaotong University in 2022. During my undergraduate studies, I spent a year (2021-2022) as an exchange student at the National University of Singapore Research Institute (Suzhou), majoring in Mechanical Engineering.

Email  /  Github  /  Google Scholar

Hantao Ye

News

Selected Publications

* represents equal contribution

Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-language Models

Mingen Li, Houjian Yu, Yixuan Huang, Youngjin Hong, Hantao Ye, Changhyun Choi

ICRA, 2026

Finalist, IEEE ICRA Best Paper Award on Robot Learning

[Project Page] [Paper] [Video]

Long-horizon routing tasks of deformable linear objects (DLOs), such as cables and ropes, are common in industrial assembly lines and everyday life. In this paper, we propose a fully autonomous hierarchical framework for solving challenging DLO routing tasks. Given an implicit or explicit routing goal expressed in language, our framework leverages vision-language models (VLMs) for in-context high-level reasoning to synthesize feasible plans, which are then executed by low-level skills trained via reinforcement learning. To improve robustness over long horizons, we further introduce a failure recovery mechanism that reorients the DLO into insertion-feasible states. It achieves an overall success rate of 92% across long-horizon routing scenarios.

Real-to-Sim Parameter Learning for Deformable Packages Using High-Fidelity Simulators for Robotic Manipulation

Omey M. Manyar*, Hantao Ye*, Siddharth Mayya, Fan Wang, Satyandra K. Gupta

IDETC-CIE, 2025

[Project Page] [Paper] [Code]

Deformable packages are becoming increasingly prevalent in the logistics and warehouse industry, demanding robotic manipulation strategies that are robust and adaptive. In this work, we present a physics-driven simulation framework that accurately models multi-object deformable packages, capturing package deformations, suction-cup interactions, and internal object dynamics. By leveraging high-fidelity physics, we optimize simulation parameters using real-world trajectory and package deformation data, ensuring an accurate representation of package behavior.

Simulation-Assisted Learning for Efficient Bin-Packing of Deformable Packages in a Bimanual Robotic Cell

Omey M. Manyar*, Hantao Ye*, Meghana Sagare, Siddharth Mayya, Fan Wang, Satyandra K. Gupta

IROS, 2024

[Project Page] [Paper] [Code]

Bin-packing is an important problem in the robotic warehouse domain. Traditionally, this problem has been studied only for rigid packages (e.g., boxes or rigid objects). In this work, we tackle the problem of bin-packing with deformable packages that have become a popular choice for fulfillment needs. We present a system that incorporates a dual robot arm bimanual setup, uniquely combining suction and sweeping motions to stably and reliably pack deformable packages in a bin.

Selected Projects

YOLO-V8 Based Package Segmentation and Sorting

RRoS-Lab, USC

May 2023 - August 2023

[Demo]

We developed a bimanual robotic system that utilized two robots for package handling: one for placing packages into a bin and another for stowing them, achieving an 89% success rate in 100 trials. This system integrated the Yolo v8 object detection model with the MoveIt planning interface for precise package detection and handling. Additionally, I built an offline planning database that generated optimal robotic paths, enhancing the efficiency and reliability of the operation.

Academic Service