ZiangZheng

About Me

I am a Ph.D. 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] A Path-Driven Probabilistic Framework for Abnormal Behavior Simulation accepted to IV 2025.
• [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] Published Adaptive Device Sampling and Deadline Determination in Journal of Cloud Computing.

Publications

Services

Conference Reviewers

• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021-2023
• IEEE/CVF International Conference on Computer Vision (ICCV) 2021
• European Conference on Computer Vision (ECCV) 2022

Journal Reviewers

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• International Journal of Computer Vision (IJCV)

Powered by Jekyll and Minimal Light theme.