Hao Zhang

Hao Zhang

Ph.D.
Research Fellow

I am the Associate Director of the ETAIC (Embodied Technology for Autonomy, Intelligence, and Control) Research Lab at the University of Texas at Arlington, working with Prof. Eric Tseng, a member of the National Academy of Engineering. I am currently conducting postdoctoral research in the Safe AI Lab at Carnegie Mellon University, working with Prof. Ding Zhao. Prior to this, I worked as a Research Fellow at Tsinghua University and a Visiting Researcher at University College of London. I received my Ph.D. from School of Vehicle and Mobility at Tsinghua University, co-advised by Prof. Zhi Wang and Prof. Shengbo Eben Li.

I was the recipient of the Outstanding Doctoral Dissertation Award, the Outstanding Ph.D. Graduate, and the “Shuimu Scholar” talent program at Tsinghua University in 2024. My doctoral research directly contributed to the successful industry deployment of reinforcement learning methods in developing advanced driver-assistance systems and energy management systems, significantly improving safety, drivability, energy efficiency, and driving comfort, thereby enhancing the overall driving experience of connected and automated vehicles. Notably, the control systems I developed have been implemented in leading automotive companies such as BYD Auto, Dongfeng Motor, SAIC Motor, and start-up automotive companies such as Hybot.

I have authored over 50 peer-reviewed SCI journal and conference papers and am a co-inventor on more than 20 patents. I serve as Guest Editor for several journals and as Associate Editor on the International Program Committee of several conferences including IEEE ITSC, IEEE IV, etc. My current research focuses on multi-agent reinforcement learning theory, the integration of large language models with closed-loop control, and human–robot collaboration using game theory. I aim to advance human-centric trustworthy AI agents for real-world deployment in autonomous systems.

💻 Research Interests

  • Embodied AI theory: Learning-based control, Multi-agent reinforcement learning, and game theory
  • Robotics: Trustworthy AI methods for decision-making and control of assistive and mobile robots
  • Intelligent vehicles: Human-centric AI for ADAS and EMS to improve safety, drivability, efficiency, and comfort
Demo 1
Multi-Agent Safe Decision Making
Demo 2
Trustworthy AI Partner
Demo 3
Contact-Rich Whole body Control
Demo 4
Intelligent Vehicle and Digital Twin

🔥 News

📝 Featured Publications

Preprint
sym

Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization

Hao Zhang, Yaru Niu, Yikai Wang, Ding Zhao, H. Eric Tseng
Under review

Project Webpage

  • We propose heterogeneous-agent Lyapunov policy optimization (HALyPO), which establishes formal stability directly in the policy-parameter space by enforcing a per-step Lyapunov decrease condition on a parameter-space disagreement metric.
Preprint
sym

C2C: A Cognition-to-Control Hierarchy for Human-Robot Collaboration via Multi-Agent Learning

Hao Zhang, Ding Zhao, H. Eric Tseng
Under review

Project Webpage

  • In multi-agent human-robot collaboration, where long-horizon coordination decisions and physical execution must co-evolve under contact, feasibility, and safety constraints. We address this limitation with cognition-to-control (C2C), a three-layer hierarchy that makes the deliberation-to-control pathway explicit.
IEEE TITS
sym

Multi-Scale Reinforcement Learning of Dynamic Energy Controller for Connected Electrified Vehicles

Hao Zhang, Nuo Lei, Shengbo Eben Li, Junzhi Zhang, Zhi Wang
In IEEE Transactions on Intelligent Transportation Systems

  • We proposed a multi-horizon reinforcement learning (MHRL) featuring a novel state representation and coordinated training of sub-networks across multiple time scales, which greatly improves fuel economy in real-world driving.
Preprint
sym

IO-WBC: Interaction-Orientated Whole-Body Control for Compliant Object Transport

Hao Zhang, Yves Tseng, Ding Zhao, H. Eric Tseng
Under review

Project Webpage

  • We proposed a bio-inspired, interaction-oriented whole-body control (IO-WBC) that functions as an artificial cerebellum - an adaptive motor agent that translates upstream (skill-level) commands into stable, physically consistent whole-body behavior under contact.
IEEE TITS
sym

Bi-Level Transfer Learning for Lifelong-Intelligent Energy Management of Electric Vehicles

Hao Zhang, Nuo Lei, Wang Peng, Bingbing Li, Shujun Lv, Boli Chen, Zhi Wang
In IEEE Transactions on Intelligent Transportation Systems

Industrial Collaborator: BYD Auto

  • We proposed a bi-level transfer approach with MAML to realize cross-platform transferable and online-adaptive EMS for REEVs. It contributed to the successful industry deployment of RL methods, implemented in leading automotive company - BYD Auto, significantly enhancing the REEV efficiency.
Energy
sym

Modeling and control system optimization for electrified vehicles: A data-driven approach

Hao Zhang, Nuo Lei, Boli Chen, Bingbing Li, Rulong Li, Zhi Wang
In Energy

Industrial Collaborator: Dongfeng Motor

  • This paper develops a high-fidelity PHEV model integrating physical and data-driven approaches, and proposes a real-vehicle control framework that combines horizon-extended reinforcement learning with ECMS to improve practical energy management.
IEEE TVT
sym

Theory-Constrained Neural Network with Modular Interpretability for Fuel Cell Vehicle Modelling

Nuo Lei, Hao Zhang* (Corresponding Author), Hong Wang, Zunyan Hu, Hu Chen, Jingjing Hu, Zhi Wang
In IEEE Transactions on Vehicular Technology

Industrial Collaborator: Hybot

  • We proposed a theory-constrained neural network (TCNN) that integrates physical principles without sacrificing accuracy. A theory-guided filter ensures sub-module interpretability, and sub-networks are individually trained under theoretical constraints with a CNN-BiLSTM-MHSA architecture enhances overall accuracy. Results demonstrate significant improvements in fitting accuragy for fuel cell modeling.
Aplied Energy
sym

Coupled velocity and energy management optimization of connected hybrid electric vehicles for maximum collective efficiency

Hao Zhang, Boli Chen, Nuo Lei, Bingbing Li, Chaoyi Chen, Zhi Wang
In Applied Energy

  • This paper proposes an efficient nested parallel optimization (NPO) strategy based on the ‘1+n’ mixed platoon concept, integrating Pontryagin’s minimum principle into a constrained control framework to jointly optimize speed planning and energy control of heterogeneous CAVs. The method reduces the control state-action dimensions while balancing traffic efficiency and fuel economy across intersections.
IEEE TTE
sym

Integrated Thermal and Energy Management of Connected Hybrid Electric Vehicles Using Deep Reinforcement Learning

Hao Zhang, Boli Chen, Nuo Lei, Bingbing Li, Rulong Li, Zhi Wang
In IEEE Transactions on Transportation Electrification

Industrial Collaborator: Dongfeng Motor

  • This research proposes a model-free multistate deep reinforcement learning (DRL) algorithm for integrated thermal and energy management (ITEM) of multimode connected PHEVs, leveraging AI control and traffic preview to enhance EMS performance under cold climate conditions.

Preprints

  • Zhang H, Yaru Niu, Yikai Wang, Ding Zhao, H. Eric Tseng. Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization. arXiv, 2026, under review.
  • Zhang H, Ding Zhao, H. Eric Tseng. C2C: A Cognition-to-Control Hierarchy for Human-Robot Collaboration via Multi-Agent Learning. arXiv, 2026, under review.
  • Zhang H, Yves Tseng, Ding Zhao, H. Eric Tseng. IO-WBC: Interaction-Orientated Whole-Body Control for Compliant Object Transport. arXiv, 2026, under review.
  • Zhang H, H. Eric Tseng. Intention-Aware Adversarial MARL for AV Stress Testing. arXiv, 2025, under review.
  • Mubai Ding, Yisen Li, et al., Zhang H* (Corresponding Author). Learning-augmented optimization and control of long-haul mobility propulsion systems. iScience (Cell Press), 2025, under review.
  • Xinyi Zhao, Nuo Lei, et al., Zhang H* (Corresponding Author). Adversarial experience replay in embodied multi-agent learning for efficient coordination of wheel-legged mobile robots. Engineering Applications of Artificial Intelligence, 2025, under review.

Selected Papers

  • Zhang H, Lei N, Li E S, et al. Multi-scale reinforcement learning of dynamic energy controller for connected electrified vehicles. IEEE Transactions on Intelligent Transportation Systems, 2025, Early Acess.
  • Yang G, Zhang H, Qiu L. Graph-based multi-agent reinforcement learning with an enriched environment for joint ride-sharing and charging optimization. Applied Energy, 2025,405:127220.
  • Zhang H, Dong J, Lei N, et al. Optimal vehicle dynamics and powertrain control of carbon-free autonomous vehicles: Large Language Model Assisted Heterogeneous-Agent Learning. Energy, 2025,338:138786
  • Sun Y, Zhang H*, Lei N, et al. Exergy analysis-based topology optimization of ammonia-hydrogen propulsion system for carbon-free heavy vehicles. International Journal of Hydrogen Energy, 2025,203:153041.
  • Li B, Wang K, Zhang H, et al. A Globally Tuned Load-Leveling Strategy for Energy Management of Hybrid Electric Vehicles. Energy, 2025,336:138346
  • Zhang H, Lei N, Chen B, et al. Bi-level transfer learning for lifelong intelligent energy management of electric vehicles. IEEE Transactions on Intelligent Transportation Systems, 2025,26:16174-16187.
  • Zhang H, Yang G, Lei N, et al. Scenario-aware electric vehicle energy control with enhanced vehicle-to-grid capability: A multi-task reinforcement learning approach. Energy, 2025,138189.
  • Zhang H, Xu J, Lei N, et al. Surrogate-enhanced multi-objective optimization of on-board hydrogen production device for carbon-free heavy-duty vehicles. Energy, 2025,333:137369.
  • Lei N, Zhang H, Hu J, et al. Sim-to-real design and development of reinforcement learning-based energy management strategies for fuel cell electric vehicles. Applied Energy, 2025,393:126030.
  • Lei N, Zhang H* (Corresponding Author), Wang H, et al. Theory-Constrained Neural Network with Modular Interpretability for Fuel Cell Vehicle Modelling. IEEE Trans. on Vehicular Technology, 2025, Early Access.
  • Zhang H, Lei N, Chen B, et al. Modeling and control system optimization for electrified vehicles: A data-driven approach. Energy, 2024,311:133196.
  • Zhang H, Chen B, Lei N, et al. Coupled velocity and energy management optimization of connected hybrid electric vehicles for maximum collective efficiency. Applied Energy, 2024,360:122792.
  • Li B, Zhuang W, Zhang H, et al. Traffic-aware ecological cruising control for connected electric vehicle. IEEE Trans. on Transportation Electrification. 2024,10:5225-5240.
  • Zhang H, Chen B, Lei N, et al. Integrated thermal and energy management of connected hybrid electric vehicles using deep reinforcement learning. IEEE Trans. on Transportation Electrification, 2024,10:4594-4603.
  • Lei N, Zhang H, and Wang Z. A comprehensive study of various carbon-free vehicle propulsion systems utilizing ammonia-hydrogen synergy fuel. eTransportation, 2024,20:100332.
  • Zhang H, Lei N, Wang Z. Ammonia-hydrogen propulsion system for carbon-free heavy-duty vehicles. Applied Energy, 2024,369:123505.
  • Sun H, Li B, Zhang H, et al. Ecological electric vehicle platooning: an adaptive tube-based distributed model predictive control approach. IEEE Trans. on Transportation Electrification, 2024,11:1048-1060.
  • Lei N, Zhang H, Li R, et al. Physics-informed data-driven modeling approach for commuting-oriented hybrid powertrain optimization. Energy Conversion and Management, 2024;299:117814.
  • Zhang H, Lei N, Chen B, et al. Data-driven predictive energy consumption minimization strategy for connected plug-in hybrid electric vehicles. Energy, 2023,283:128514.
  • Li B, Zhuang W, Zhang H, et al. A comparative study of energy-oriented driving strategy for connected electric vehicles on freeways with varying slopes. Energy, 2023,289:129916.
  • Lei N, Zhang H, Wang H, et al. An improved co-optimization of component sizing and energy management for hybrid powertrains with high-fidelity model. IEEE Trans. on Vehicular Technology, 2023,72:15585-15596.
  • Zhang H, Liu S, Lei N, et al. Learning-based supervisory control of dual mode engine-based hybrid electric vehicle with reliance on multivariate trip information. Energy Conversion and Management, 2022,257:115450.
  • More publications can be found on my Google Scholar homepage.

Book Chapters

  • Bin Shuai, Hao Zhang (Co-first Author), Min Hua, et al. Physics-Aware Machine Learning for Integrated Energy Systems Management. ELSEVIER.

🎖 Honors and Awards

  • 2024 Plenary Talk at 2024 China SAE Annual Conference on Advanced Powertrains
  • 2024 “Shuimu Tsinghua Scholar” Talents Program, Tsinghua University
  • 2024 Outstanding Doctoral Dissertation Award, Tsinghua University
  • 2024 Outstanding Ph.D. Graduate (top 4%), Tsinghua University
  • 2023 Comprehensive Excellence Scholarship, Tsinghua University
  • 2022 Best Paper Award in the 2022 CSICE Conference on TEIP in Shanghai, China
  • 2022 Comprehensive Excellence Scholarship, Tsinghua University
  • 2021 Excellent Student Leader, Tsinghua University
  • 2021 Comprehensive Excellence Scholarship, Tsinghua University
  • 2020 Comprehensive Excellence Scholarship, Tsinghua University
  • 2018 National Scholarship, Ministry of Education of China
  • 2018 Best Paper Award in the 2018 IEEE ACES Conference in Denver, U.S.
  • 2017 National Scholarship, Ministry of Education of China
  • 2016 National Scholarship, Ministry of Education of China

💬 Invited Talks

  • 2024.08, Plenary Talk, APC 2024: Joint Annual Conference on Advanced Powertrains - China SAE, “Data-Driven Modeling of Electric Powertrains and Reinforcement Learning-Based Optimal Control,” China SAE, Zhenjiang, China

📚 Service

Reviewer

  • Reviewer, Journal, IEEE Transactions on Intelligent Transportation Systems
  • Reviewer, Journal, IEEE Transactions on Intelligent Vehicles
  • Reviewer, Journal, IEEE Transactions on Transportation Electrification
  • Reviewer, Journal, IEEE Transactions on Vehicular Technology
  • Reviewer, Journal, IEEE Open Journal of Vehicular Technology
  • Reviewer, Journal, Renewable and Sustainable Energy Reviews
  • Reviewer, Journal, Applied Energy
  • Reviewer, Journal, Energy
  • Reviewer, Journal, Sustainable Energy, Grids and Networks
  • Reviewer, Journal, Energy Conversion and Management
  • Reviewer, Journal, Journal of Cleaner Production
  • Reviewer, Journal, Engineering Applications of Artificial Intelligence
  • Reviewer, Conference, IEEE Intelligent Vehicles Symposium (IV)
  • Reviewer, Conference, IEEE Intelligent Transportation Systems Conference (ITSC)
  • Associate Editor, IEEE Intelligent Vehicles Symposium (IEEE IV), sponsored by The IEEE Intelligent Transportation Systems Society (ITSS), Ann Arbor, USA
  • Associate Editor, The IEEE International Conference on Intelligent Transportation Systems (ITSC), sponsored by The IEEE Intelligent Transportation Systems Society (ITSS), Naples, Italy
  • Guest Editor, Electronics, Special Issue: Eco-Safe Intelligent Mobility Development and Application

Teaching

  • Guest Lecturer, 80150183, Fundamentals of Automotive Powertrains, Tsinghua University, Fall 2023
  • Teaching Assistant, 40150420, Student Research Training (SRT), Tsinghua University, Fall 2022
  • Teaching Assistant, 80150042, Frontiers in Vehicle System Dynamics and Control, Tsinghua University, Fall 2021

Mentorship

  • Since 2024, independently mentored postgraduate and undergraduate students from THU, UC Berkeley, UCL, NYU, Brown, HKU, ZJU, etc. Several undergraduate/master mentees have published papers in top-tier journals such as Engineering Applications of Artificial Intelligence, Applied Energy, Energy, etc.
  • Since 2020, assisted in the supervision of 3 Ph.D. students, 5 master’s students; mentored over a dozen undergraduate students, their work received multiple honors including Tsinghua University and Beijing Outstanding Undergraduate Thesis Awards.