Research Highlights

Many real-world systems usually have complex nonlinear dynamics, and need to operate in dynamic environments subject to model uncertainties due to physical failures, unmodeled dynamics, and external disturbances. High-performance control algorithms considering the nonlinear and uncertain dynamics are crucial for ensuring the safety and efficiency of the systems.  Over the years, we have developed innovative adaptive and robust control algorithms designed to achieve efficient control of uncertain systems, offering formal guarantees of both safety and performance. Key highlights of these developments include: 

• tube-certified robust control of nonlinear uncertain systems based on contraction theory [1,2]

• adaptive control of systems with large operating envelopes [3,4,5]

• integrated adaptive control and reference governor/MPC for efficient constrained control of uncertain systems [6,7]

Relevant publications

1. P. Zhao, A. Lakshmanan, K. Ackerman, A. Gahlawat, M. Pavone, and N. Hovakimyan. “Tube-certified trajectory tracking for nonlinear systems with robust control contraction metrics.” IEEE Robotics and Automation Letters, 2022.

2. P. Zhao, Z. Guo, and N. Hovakimyan. “Robust nonlinear tracking control with exponential convergence using contraction metrics and disturbance estimation.” Sensors, 2022. 

3.  P. Zhao, S. Snyder, N. Hovakimyan, and C. Cao. “Robust adaptive control of linear parameter-varying systems with unmatched uncertainties.” Journal of Guidance, Control, and Dynamics, 47(10): 2085-2102, 2024. 

4. S. Snyder, P. Zhao†, and N. Hovakimyan. “L1 adaptive control with switched reference models: Application to Learn-to-Fly.” Journal of Guidance, Control, and Dynamics, 45(12): 2229-2242, 2022

5. S. Snyder, P. Zhao, and N. Hovakimyan. “Adaptive control for linear parameter-varying systems with application to a VTOL aircraft.” Aerospace Science and Technology, 112: 106621, 2021. 

6. P. Zhao, I. Kolmanovsky, and N. Hovakimyan. “Integrated adaptive control and reference governors for constrained systems with state-dependent uncertainties.” IEEE Transactions on Automatic Control, 69(5):3158-3173, 2024.

7. R. Tao, P. Zhao, I. Kolmanovsky, and N. Hovakimyan. “Robust adaptive MPC using uncertainty compensation,” 2024 American Control Conference, pp. 1873-1878, 2024. 

We develop novel safe and robust learning-enabled control algorithms by holistically integrating machine learning and robust/adaptive control theory. In particular, we leverage adaptive control to actively compensate for the uncertainties that may be induceby environmental change (in a model-free setting) or the inaccuracy of the learned dynamics (in a model-based setting). This uncertainty compensation-based approach enables a fast reaction to sudden dynamics change and less conservative control performance in the presence of a poorly learned dynamics model compared to robust approaches without uncertainty compensation.

Relevant publications

1. Y. Cheng, P. Zhao, F. Wang, D. J. Block, and N. Hovakimyan. “Improving the robustness of reinforcement learning policies with L1 adaptive control.” IEEE Robotics and Automation Letters, 2022. 

2. Y. Cheng, P. Zhao, and N. Hovakimyan. “Safe model-free reinforcement learning using disturbance-observer-based control barrier functions,” 5th Conference on Learning for Dynamics and Control, 2023.

3. P. Zhao, Z. Guo, Y. Cheng, A. Gahlawat, H. Kang, and N. Hovakimyan. “Guaranteed nonlinear tracking under learned dynamics with contraction metrics and disturbance estimation.” Robotics, 13(7):99, 2024. 

4. A. Gahlawat, P. Zhao, A. Patterson, N. Hovakimyan, and E. A. Theodorou. “L1-GP: L1 adaptive control with Bayesian learning.” 2nd Conference on Learning for Dynamics and Control (L4DC), 2020.

We develop advanced control algorithms for aerospace and robotic vehicles to ensure their safe and efficient operation in challenging environments. The following video demonstrated the superior performance of our adaptive geometric controller in various scenarios including unknown payload, ground effect, propeller damage, down-wash effect, and sudden change of payload.

Relevant publications

1. Z. Wu, S. Cheng, P. Zhao, et al. “L1Quad: L1 adaptive augmentation of geometric control for agile quadrotors with performance guarantees.” IEEE Transactions on Control System Technology, Early Access, 2024. 

2. Z. Wu, C. Sheng, K. A. Ackerman, A. Gahlawat, A. Lakshmanan, P. Zhao, and N. Hovakimyan. “L1 adaptive augmentation for geometric tracking control of quadrotors,” IEEE International Conference on Robotics and Automation (ICRA), 2022. 

3. P. Zhao, A. Hallmark, and J.D. Larson. "Constrained control of lift-plus-cruise VTOL aircraft using reference governors". In AIAA SCITECH 2025 Forum (p. 0934), 2025. 

The world's agricultural system is facing significant challenges to bridge the gap between the amount of food produced today and that needed to feed a population of 9.6 billion by 2050 while reducing environmental impacts. In this project, we envisioned an intelligent agricultural management system based on deep reinforcement learning (RL) and crop simulations (e.g., using DSSAT), which can improve crop yields while reducing the use of resources (e.g., fertilizers, irrigation water) compared to expert-suggested management practices. We also leveraged imitation learning (IL) to train practically-implementable management policies that use only the state information that is easily accessible in the real world.

Relevant publications

1. J. Wu, Z. Lai, S. Chen, R. Tao, P. Zhao, and N. Hovakimyan. "The new agronomists: Language models are experts in crop management." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 5346-5356, 2024.

2. R. Tao, P. Zhao, J. Wu, N. F. Martin, M. T. Harrison, C. Ferreira, Z. Kalantari, and N. Hovakimyan. “Optimizing Crop management with reinforcement learning and imitation learning,” Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23), pp. 6228-6236, 2023. 

3. J. Wu, R. Tao, P. Zhao, N. Martin, and N. Hovakimyan. “Optimizing nitrogen management with deep reinforcement learning and crop simulations,” Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.