Yutong Hu <span style='white-space: nowrap;'>胡雨桐</span>

Yutong Hu 胡雨桐

I am currently a research assistant at Visual Intelligence and System Group, Computer Vision Lab, ETH Zurich, working on visual-motor policy for manipulator and legged robots.

I graduated from ShenYuan Honors College, Beihang University (Beijing University of Aeronautics and Astronautics, BUAA) with a Bachelor’s degree and from the Robotics Institute of Beihang University with a Master’s degree, supervised by Prof. Wang Wei.

While my current research focuses on how (data-driven) perceptions and control can make robots more autonomous and intelligent, I also have a strong passion for hardware design and real world experiments, stemming from my background as an engineering student who embarked from the field of Mechatronics.

For more details, please check my published papers about SLAM and Robot Learning. You can also have a look at my previous tiny projects about robotics and automation.

📝 Publications

Preprint

Masked all-in-one Transformer for Bi-directional Model Predictive Control

Yutong Hu*, et al. | Code

  • Enhance Masked Transformer for Offline RL by employing versatile capabilities from the Model itself for runtime Predictive Control.
  • Achieve better performance in offline RL and offline-to-online RL for both simulated and real-world robotic tasks, with additional goal-reaching capabilities.
IROS 2024

DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision

Yutong Hu*, Wenke Han, Fisher Yu, Yifan Liu

Project | Code

  • Make quadrupedal robot able to dribble and kick soccer ball using only ego-vision camera and onboard sensors.
  • Transfer the skill from Sim to Real by using a virtual Feedback Controller to guide the Deep Reinforcement Learning process of a implicit Policy Network from Massively Parallel Simulation.
RA-L & IROS 2022

Making Parameterization and Constrains of Object Landmark Globally Consistent via SPD (3) Manifold

Yutong Hu, Wei Wang*

  • Propose A Mono-camera SLAM system that can provide map with sematic-meaningful Ellipsoid landmarks to represent object in the indoor scenes.
  • Further improvements on the representation of the 9-DOF object landmarks (Rotation, Translation, Scale), resulting in an improved Object SLAM system with faster and more accurate back-end mapping manifold optimization process.
RA-L & ICRA 2022
sym

SO-SLAM: Semantic object slam with scale proportional and symmetrical texture constraints

Ziwei Liao, Yutong Hu, Jiadong Zhang, Xianyu Qi, Xiaoyu Zhang, Wei Wang*

  • Enhance monocular object SLAM algorithm by fully coupling three spatial structure (Symmetrical, Plane-Tangent, Scale) constraints for indoor environments.
  • Propose a sampling-based method to detect the texture symmetry for objects in monocular images.

⚙️ Tiny Projects

Image 1

Dragon-like Worm

Image 2
8-bar Linkage Walker
Image 3
Smartphone-controlled Paper Plane
Image 4
Maglev Prototype
Image 5
2-joint Maze Solver
Image 6
Sim2Real Grasping

📖 Educations

  • 2020.09 - 2023.03： M.Phil., the Robotics Institute, School of Mechanical Engineering and Automation, Beihang University
  • 2016.09 - 2020.06： B.Eng., ShenYuan Honors College, Beihang University

💻 Internships

  • 2023.07 - 2024 (Now)： Research Assistant @ Visual Intelligence and System Group, Computer Vision Lab, ETH Zurich.
  • 2022.05 - 2022.11： Research Intern @ Samsung Research Center, Beijing.

🎖 Honors and Awards

  • 2023.03： Graduate Excellence in Beijing Province
  • 2023.01： Samsung 2022 Best Intern
  • 2023.01： Outstanding Master Thesis Award in Beihang University
  • 2022.12： Robotics Institute Founder’s Scholarship (1/year)
  • 2016, 2018-2019, 2020, 2022： Annual Full Scholarship