Wenjian Hao
Ph.D. candidate, Purdue University AAE

Short Biography

I am a Ph.D. candidate in the School of Aeronautics and Astronautics at Purdue University, advised by Dr. Shaoshuai Mou. My research focuses on learning-based control for autonomous robots; data-driven modeling of nonlinear dynamics using globally linear representations; data-efficient reinforcement learning; optimal, safety-critical, and sampling-based control; and multi-agent systems.

Wenjian Hao portrait

Highlighted Work

Efficient reinforcement learning robotic arm animation
Efficient reinforcement learning using linear Koopman dynamics for nonlinear robotic systems
This paper presents an online model-based reinforcement learning framework that combines learned linear Koopman...
2026 · [PDF]
Accelerating sampling-based control robot motion latest animation
Accelerating sampling-based control via learned linear Koopman dynamics
This paper presents an efficient MPPI control framework using learned linear Koopman dynamics to reduce rollout...
2026 · [PDF] / [Code]
Control-barrier-function-based policy adaptation robot motion latest animation
A control-barrier-function-based algorithm for policy adaptation in reinforcement learning
This paper formulates policy adaptation as constrained optimization and uses control barrier functions to...
2025 · [PDF] / [Code]
Optimal control of nonlinear systems quadruped animation
Optimal control of nonlinear systems with unknown dynamics
This paper presents a data-driven actor-critic Koopman framework for closed-loop optimal control of systems...
2023 · [PDF] / [Code]
Deep Koopman learning time-varying systems gamma comparison animation
Deep Koopman learning of nonlinear time-varying systems
This paper proposes deep Koopman learning for nonlinear time-varying systems with error analysis and...
Automatica 2024 · [PDF] / [Code]
Deep learning of Koopman representation for control RC car optimized animation
Deep learning of Koopman representation for control (* indicates equal contribution)
This paper develops a model-free control pipeline using deep Koopman representations learned directly from...
CDC 2020 · [PDF] / [Code]
Deep Koopman learning using noisy data figure
Deep Koopman learning using noisy data
This paper develops deep Koopman learning under bounded measurement noise by explicitly modeling and mitigating...
TMLR 2025 · [PDF] / [Code]
Distributed Koopman Learning using Partial Trajectories for Control
Distributed Koopman learning using partial trajectories for control
This paper proposes distributed deep Koopman learning with partial trajectories, allowing consensus dynamics...
ACC 2026 · [PDF] / [Code]
Distributed Koopman Learning with Incomplete Measurements
Distributed Koopman learning with incomplete measurements
This paper develops distributed Koopman learning for networks with partial observations, enabling cooperative...
2024 · [PDF] / [Code]
RefleXAI autonomous surface vehicle project figure
C3d: cascade control with change point detection and deep Koopman learning for autonomous surface vehicles
This paper introduces C3D, a modular ASV control architecture combining deep Koopman learning and change-point...
2024 · [PDF] / [Code]
Data-driven inverse optimal control figure
A data-driven approach for inverse optimal control
This paper proposes an iterative data-driven inverse optimal control method that jointly learns unknown...
CDC 2023 · [PDF] / [Code]

Projects

Automatic Trading Platform
Automatic Trading Platform
Project goal: Designed and developed an automatic trading platform for quantitative strategy...
March 2026
Explainable Reflexive Control (RefleXAI)
Explainable Reflexive Control (RefleXAI)
Project goal: RefleXAI is a DARPA-backed effort on adaptive control for uncrewed sea vessels...
August 2022
Secure and Safe Assured Autonomy (S2A2)
Secure and Safe Assured Autonomy (S2A2)
Project goal: S2A2 is a NASA University Leadership Initiative project focused on secure and...
August 2021
Virtual Prototyping of Autonomy-Enabled Ground Systems (VIPR-GS)
Virtual Prototyping of Autonomy-Enabled Ground Systems (VIPR-GS)
Project goal: VIPR-GS advances virtual prototyping methods for autonomy-enabled ground systems....
October 2020

Blog

Learning nonlinear systems using linear operators and machine learning
A concise introduction to learning nonlinear systems using linear operators and machine learning for prediction and control.
March 2026

Miscellaneous

News
Updates, announcements, and short highlights.
March 2026