ZiangZheng | Tsinghua University

About Me

I am a Mphil. student at Tsinghua University working on robot learning, with a focus on data-driven whole-body control, embodied intelligence, and safe reinforcement learning. My research spans the intersection of control theory, machine learning, and robot locomotion, aiming to build generalizable, efficient, and physically consistent motion control systems for diverse robotic platforms.

Research Interests

Robot Learning: whole-body control, reinforcement learning, safe exploration, dataset-constrained RL
Locomotion & Motion Control: latent-to-latent policy transfer, extreme locomotion, motion tracking and retargeting
Control & Optimization: MPC, Lagrangian neural networks, differentiable control
Simulation & Embodied Systems: IsaacLab, motion generation, trajectory optimization

News

[2025] Transferable Latent-to-Latent Locomotion Policy accepted to IROS 2025.
[2025] Canonical Form of Datatic Description in Control Systems accepted to ACC 2025.
[2025] Learn a Safe and Efficient MPC with Lagrange Multiplier Neural Network accepted to TCST.
[2025] Released TrackerLab, a unified whole-body control framework built on IsaacLab.
[2024] Presented DCRL: Dataset-Constrained Reinforcement Learning in Tsinghua’s Advanced ML course.
[2023] Adaptive Device Sampling and Deadline Determination accepted to JCC.

Publications

GitHub

beyondAMP: One-Step Integration of AMP into IsaacLab

Ziang Zheng

GitHub Repository, 2025.

PDF Code BibTex Open Source

arXiv

Task-Centric Policy Optimization from Misaligned Motion Priors

Ziang Zheng, Kai Feng, Yi Nie, Shentao Qin

arXiv preprint arXiv:2601.19411, 2026.

PDF Code BibTex Under Review

GitHub

TrackerLab: One Step Unify IsaacLab with Multi-Mode Whole-Body Control

Ziang Zheng

GitHub Repository, 2025.

PDF Code BibTex Open Source

arXiv

Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion

Ziang Zheng, Guojian Zhan, Shiqi Liu, Yao Lyu, Tao Zhang, Shengbo Eben Li

arXiv preprint arXiv:2507.01243, 2025.

PDF Code BibTex Under Review

IROS

Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots

Ziang Zheng, Guojian Zhan, Bin Shuai, Shengtao Qin, Jiangtao Li, Tao Zhang, Shengbo Eben Li

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.

PDF Code BibTex Accepted

TCST

Learn a Safe and Efficient Model Predictive Controller with Lagrange Multiplier Neural Network

Guojian Zhan, Ziang Zheng, Feihong Zhang, Jingliang Duan, Shengbo Eben Li, Songan Zhang, H. Eric Tseng

IEEE Transactions on Control Systems Technology (TCST), 2025.

PDF Code BibTex Early Accept

ACC

Canonical Form of Datatic Description in Control Systems

Guojian Zhan, Ziang Zheng, Shengbo Eben Li

American Control Conference (ACC), 2025.

PDF Code BibTex Accepted

AML

DCRL: Dataset-Constrained Reinforcement Learning for Safe In-Distribution Exploration

Ziang Zheng

Tsinghua University Course: Advanced Machine Learning, 2024.

PDF Code BibTex Accepted

JCC

Adaptive Device Sampling and Deadline Determination for Cloud-Based Heterogeneous Federated Learning

Deyu Zhang, Wang Sun, Zi-Ang Zheng, Wenxin Chen, Shiwen He

Journal of Cloud Computing, 2023.

PDF Code BibTex Accepted

Services

Open Source Community

Renforce Dynamics - Leader