Jiayang Wu | 吴嘉阳

Research Interests

The long-term goal of my research is to build humanoid robots that can manipulate everyday objects with human-level dexterity, and interact naturally and safely with people through scene reasoning, task planning, and robust whole-body control.

Humanoid Object Manipulation

Whole-body loco-manipulation: coordinating locomotion and dexterous manipulation for everyday objects and long-horizon tasks.

Vision-Language-Action Models

Learning generalizable manipulation policies from large-scale robot data and language-conditioned demonstrations.

Reinforcement Learning & Optimal Control

Dynamic, agile, and energy-efficient whole-body skills for full-size humanoid robots.

Publications

Dynamic Whole-Body Dancing with Humanoid Robots — A Model-Based Control Approach

Shibowen Zhang, Jiayang Wu, Guannan Liu, Helin Zhu, Junjie Liu, Zhehan Li, Junhong Guo, Xiaokun Leng, Hangxin Liu, Jingwen Zhang, Jikai Wang, Zonghai Chen, Zhicheng He, Jiayi Wang, Yao Su

IEEE Robotics & Automation Magazine (RAM) 2026

ArXiv

ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking

Weidong Huang, Jingwen Zhang, Jiongye Li, Shibowen Zhang, Jiayang Wu, Jiayi Wang, Hangxin Liu, Yaodong Yang, Yao Su

IEEE T-ASE 2026

ArXiv Code

Path and Motion Optimization for Efficient Multi-Location Inspection with Humanoid Robots

Jiayang Wu, Jiongye Li, Shibowen Zhang, Zhicheng He, Zaijin Wang, Xiaokun Leng, Hangxin Liu, Jingwen Zhang, Jiayi Wang, Song-Chun Zhu, Yao Su

arXiv 2025

ArXiv