Changhao Wang

Researcher @ Meta FAIR, Ph.D. UC Berkeley

Email: changhaowang [at] meta [dot] com


I’m a researcher at Meta Fundamental AI Research (FAIR) in Menlo Park, focusing on Robotics Manipulation and Embodied AI.

I earned my Ph.D. from UC Berkeley in Dec 2023, under the guidance of Prof. Masayoshi Tomizuka. Additionally, I had the opportunity to contribute to the Google’s Everyday Robots project in summer 2020 and 2022.

Outside of work, I am a marathon runner.


News

  • 01/2024: Paper: Distributed Multi-agent Interaction Generation with Imagined Potential Games accepted by American Control Conference (ACC) 2024.
  • 01/2024: I started as a Research Engineer in the Embodied AI team at Meta FAIR.
  • 12/2023: I successfully defended my Ph.D. dissertation and obtained the Ph.D. degree.
  • 12/2023: Paper: Robot manipulation task learning by leveraging se (3) group invariance and equivariance accpeted by IEEE Robotics and Automation Letters (RA-L).
  • 09/2023: Paper: Efficient Sim-to-real Transfer of Contact-Rich Manipulation Skills with Online Admittance Residual Learning (website) accepted by CoRL 2023.
  • 06/2023: Paper: A coarse-to-fine framework for dual-arm manipulation of deformable linear objects with whole-body obstacle avoidance (video) won the Best Paper Award at the ICRA 2023 Workshop on Representing and Manipulating Deformable Objects.
show more
  • 01/2023: Paper: A coarse-to-fine framework for dual-arm manipulation of deformable linear objects with whole-body obstacle avoidance accepted by ICRA 2023.
  • 01/2023: Paper: Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning accepted by ICRA 2023.
  • 05/2022: I begin my Resident at (Google) X, the Moonshot Factory on the Everyday Robots project.
  • 05/2022: Paper: Safe Online Gain Optimization for Cartesian Space Variable Impedance Control accepted by CASE 2022
  • 02/2022 Paper: Offline-Online Learning of Deformation Model for Cable Manipulation With Graph Neural Networks accepted by IEEE Robotics and Automation Letters (RA-L).
  • 02/2022: Paper: Robotic cable routing with spatial representation accepted by IEEE Robotics and Automation Letters (RA-L).
  • 01/2022: Paper: Learning Insertion Primitives with Discrete-Continuous Hybrid Action Space for Robotic Assembly Tasks accepted by ICRA 2022
  • 01/2022: Paper: BPOMP: A Bilevel Path Optimization Formulation for Motion Planning accepted by ACC 2022
  • 06/2021: Paper: Trajectory Splitting: A Distributed Formulation for Collision Avoiding Trajectory Optimization accepted by IROS 2021.
  • 06/2021: Paper: Online Learning of Unknown Dynamics for Model-Based Controllers in Legged Locomotion accepted by IEEE Robotics and Automation Letters (RA-L).
  • 01/2021: Paper: Contact Pose Identification for Peg-in-hole Assembly under Uncertainties accepted by ACC 2020.
  • 05/2020: I begin my robotics research intern at (Google) X, the Moonshot Factory.
  • 06/2019: Paper: Robust Deformation Model Approximation for Robotic Cable Manipulation accepted by IROS 2019.
  • 07/2019: I begin my robotics reserach intern at FANUC Advanced Reserach Laboratory.
  • 07/2018: Paper: A Framework for Manipulating Deformable Linear Objects by Coherent Point Drift accepted by IEEE Robotics and Automation Letters (RA-L).

Research

Image description

Generalizable whole-body global manipulation of deformable linear objects by dual-arm robot in 3-D constrained environments

Mingrui Yu, Kangchen Lv, Changhao Wang, Yongpeng Jiang, Masayoshi Tomizuka, Xiang Li

International Journal of Robotics Research, in submission

[Paper] [Website]

Image description

Distributed Multi-agent Interaction Generation with Imagined Potential Games

Lingfeng Sun, Pin-Yun Hung, Changhao Wang, Masayoshi Tomizuka, Zhuo Xu

American Control Conference (ACC) 2024, Accepted

[Paper] [Website] [Code]

Image description

Efficient Sim-to-real Transfer of Contact-Rich Manipulation Skills with Online Admittance Residual Learning

Xiang Zhang*, Changhao Wang*, Lingfeng Sun, Zheng Wu, Xinghao Zhu, Masayoshi Tomizuka

Conference on Robot Learning (CoRL) 2023

[Paper] [Website]

Image description

Contact-rich SE (3)-Equivariant Robot Manipulation Task Learning via Geometric Impedance Control

Joohwan Seo, Nikhil PS Prakash, Xiang Zhang, Changhao Wang, Jongeun Choi, Masayoshi Tomizuka, Roberto Horowitz

IEEE Robotics and Automation Letters (RAL) 2023

[Paper] [Website] [Code]

Image description

A coarse-to-fine framework for dual-arm manipulation of deformable linear objects with whole-body obstacle avoidance

Mingrui Yu, Kangchen Lv, Changhao Wang, Masayoshi Tomizuka, Xiang Li

ICRA 2023

Best Workshop Paper Award

[Paper] [Website] [Presentation]

Image description

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang, Yanjiang Guo, Jianyu Chen, Stefan Schaal, Masayoshi Tomizuka

ICRA 2023

[Paper]

Image description

Prim-LAfD: A Framework to Learn and Adapt Primitive-Based Skills from Demonstrations for Insertion Tasks

Zheng Wu, Wenzhao Lian, Changhao Wang, Mengxi Li, Stefan Schaal, Masayoshi Tomizuka

IFAC 2023

[Paper]

Image description

Safe online gain optimization for Cartesian space variable impedance control

Changhao Wang, Xiang Zhang, Zhian Kuang, Masayoshi Tomizuka

CASE 2022

[Paper] [Website]

Image description

Offline-Online Learning of Deformation Model for Cable Manipulation with Graph Neural Networks

Changhao Wang, Yuyou Zhang, Xiang Zhang, Zheng Wu, Xinghao Zhu, Shiyu Jin, Te Tang, Masayoshi Tomizuka

IEEE Robotics and Automation Letters (RA-L) 2022

[Paper] [Website] [Code]

Image description

Robotic Cable Routing with Spatial Representation

Shiyu Jin, Wenzhao Lian, Changhao Wang, Masayoshi Tomizuka, Stefan Schaal

IEEE Robotics and Automation Letters (RA-L) 2022

[Paper] [Code]

Image description

Learning Insertion Primitives with Hybrid Action Space for Robotic Assembly Tasks

Xiang Zhang, Shiyu Jin, Changhao Wang, Xinghao Zhu, Masayoshi Tomizuka

ICRA 2022

[Paper] [Website]

Image description

BPOMP: A Bilevel Path Optimization Formulation for Motion Planning

Changhao Wang, Hsien-Chung Lin, Shiyu Jin, Xinghao Zhu, Liting Sun, Masayoshi Tomizuka

American Control Conference (ACC) 2022

[Paper] [Website] [Patent]

Image description

Online learning of unknown dynamics for model-based controllers in legged locomotion

Yu Sun, Wyatt L Ubellacker, Wen-Loong Ma, Xiang Zhang, Changhao Wang, Noel V Csomay-Shanklin, Masayoshi Tomizuka, Koushil Sreenath, Aaron D Ames

IEEE Robotics and Automation Letters (RA-L) 2021

[Paper] [Video]

Image description

Trajectory splitting: A distributed formulation for collision avoiding trajectory optimization

Changhao Wang, Jeffrey Bingham, Masayoshi Tomizuka

IROS 2021

[Paper]

Image description

Contact pose identification for peg-in-hole assembly under uncertainties

Shiyu Jin, Xinghao Zhu, Changhao Wang, Masayoshi Tomizuka

American Control Conference (ACC) 2021

[Paper]

Image description

Robust deformation model approximation for robotic cable manipulation

Shiyu Jin*, Changhao Wang*, Masayoshi Tomizuka

IROS 2019

[Paper] [Website]

Image description

A framework for manipulating deformable linear objects by coherent point drift

Te Tang*, Changhao Wang*, Masayoshi Tomizuka

IEEE Robotics and Automation Letters (RA-L) 2018

[Paper]