Pan Zhao

University of Alabama | UA · Department of Aerospace Engineering and Mechanics

Exploring the optimal management strategy for nitrogen and irrigation has a significant impact on crop yield, economic profit, and the environment. To tackle this optimization challenge, this paper introduces a deployable \textbf{CR}op Management system \textbf{O}ver all \textbf{P}ossible \textbf{S}tate availabilities (CROPS). CROPS employs a langu...

This paper presents a contraction-based learning control architecture that allows for using model learning tools to learn matched model uncertainties while guaranteeing trajectory tracking performance during the learning transients. The architecture relies on a disturbance estimator to estimate the pointwise value of the uncertainty, i.e., the disc...

In control of aerospace systems with large operating envelopes, it is often necessary to adjust the desired dynamics according to operating conditions. This paper presents a robust adaptive control architecture for linear parameter-varying (LPV) systems that allows for the desired dynamics to be systematically scheduled, while being able to handle...

Here we generate adaptable and deployable management policies based on deep reinforcement learning (RL) and imitation learning (IL). Using N fertilization and irrigation application as examples, we use the crop model Gym-DSSAT to train several reward functions to examine trade-offs between yield, resource use and environmental impacts. We show that...

Crop management has a significant impact on crop yield, economic profit, and the environment. Although management guidelines exist, finding the optimal management practices is challenging. Previous work used reinforcement learning (RL) and crop simulators to solve the problem, but the trained policies either have limited performance or are not depl...

L_1$ adaptive control ($L_1$AC) is a control design technique that can handle a broad class of system uncertainties and provide transient performance guarantees. In this work-in-progress abstract, we discuss how existing formal verification tools can be applied to check the performance of $L_1$AC systems. We show that the theoretical transient perf...

Quadrotors that can operate safely in the presence of imperfect model knowledge and external disturbances are crucial in safety-critical applications. We present L1Quad, a control architecture for quadrotors based on the L1 adaptive control. L1Quad enables safe tubes centered around a desired trajectory that the quadrotor is always guaranteed to re...

The European Mediterranean region is heralded globally for both its high vulnerability to soil degradation and realization of the climate crisis, with ambient temperatures increasing at rates 20% faster than the global average. Maize crops in this region experience moderate to severe water stress during late spring and summer, although such trends...

This paper presents a systematic method based on the sum of square (SOS) optimization to synthesize control barrier functions (CBFs) for nonlinear polynomial systems subject to input constraints. The approach consists of two design steps. In the first step, using a linear-like representation of the nonlinear dynamics, an SOS optimization problem is...

This paper presents an adaptive reference governor (RG) framework for a linear system with matched nonlinear uncertainties that can depend on both time and states, subject to both state and input constraints. The proposed framework leverages an ( $\mathcal{L}_{1}$ ) adaptive controller ( $\mathcal{L}_{1}$ AC). that compensates for the uncertainti...

Safe reinforcement learning (RL) with assured satisfaction of hard state constraints during training has recently received a lot of attention. Safety filters, e.g., based on control barrier functions (CBFs), provide a promising way for safe RL via modifying the unsafe actions of an RL agent on the fly. Existing safety filter-based approaches typica...

This paper presents a safe stochastic optimal control method for networked multi-agent systems (MASs) by using barrier states (BaSs) to embed the safety constraints into the system dynamics. The networked multi-agent system (MAS) is factorized into multiple subsystems, each of which is augmented with BaSs for the central agent. The optimal control...

Crop management, including nitrogen (N) fertilization and irrigation management, has a significant impact on the crop yield, economic profit, and the environment. Although management guidelines exist, it is challenging to find the optimal management practices given a specific planting environment and a crop. Previous work used reinforcement learnin...

Learn-to-Fly (L2F) is a new framework that aims to replace the traditional iterative development paradigm for aerial vehicles with a combination of real-time aerodynamic modeling, guidance, and learning control. To ensure safe learning of the vehicle dynamics on the fly, this paper presents an L1 adaptive control (L1AC)-based scheme, which actively...

This paper presents an adaptive reference governor (RG) framework for a linear system with matched nonlinear uncertainties that can depend on both time and states, subject to both state and input constraints. The proposed framework leverages an L1 adaptive controller (L1AC) that estimates and compensates for the uncertainties, and provides guarante...

A reinforcement learning (RL) control policy could fail in a new/perturbed environment that is different from the training environment, due to the presence of dynamic variations. For controlling systems with continuous state and action spaces, we propose an add-on approach to robustifying a pre-trained RL policy by augmenting it with an ${\mathcal...

Nitrogen (N) management is critical to sustain soil fertility and crop production while minimizing the negative environmental impact, but is challenging to optimize. This paper proposes an intelligent N management system using deep reinforcement learning (RL) and crop simulations with Decision Support System for Agrotechnology Transfer (DSSAT). We...

This paper presents a tracking controller for nonlinear systems with matched uncertainties based on contraction metrics and disturbance estimation that provides exponential convergence guarantees. Within the proposed approach, a disturbance estimator is proposed to estimate the pointwise value of the uncertainties, with a pre-computable estimation...

Nitrogen (N) management is critical to sustain soil fertility and crop production while minimizing the negative environmental impact, but is challenging to optimize. This paper proposes an intelligent N management system using deep reinforcement learning (RL) and crop simulations with Decision Support System for Agrotechnology Transfer (DSSAT). We...

This letter presents an approach to guaranteed trajectory tracking for nonlinear control-affine systems subject to external disturbances based on robust control contraction metrics (CCM) that aims to minimize the $\mathcal {L}_\infty$ gain from the disturbances to nominal-actual trajectory deviations. The guarantee is in the form of invariant tub...

This paper presents an approach for trajectory-centric learning control based on contraction metrics and disturbance estimation for nonlinear systems subject to matched uncertainties. The approach allows for the use of a broad class of model learning tools including deep neural networks to learn uncertain dynamics while still providing guarantees o...

A reinforcement learning (RL) control policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. For controlling systems with continuous state and action spaces, we propose an add-on approach to robustifying a pre-trained RLpolicy by augmenting it with an L1 adaptive controller (L1A...

This paper introduces an $\mathcal{L}_1$ adaptive control augmentation for geometric tracking control of quadrotors. In the proposed design, the $\mathcal{L}_1$ augmentation handles nonlinear (time- and state-dependent) uncertainties in the quadrotor dynamics without assuming/enforcing parametric structures, while the baseline geometric controller...

This paper presents an approach to guaranteed trajectory tracking for nonlinear control-affine systems subject to external disturbances based on robust control contraction metrics (CCM) that aim to minimize the $\mathcal{L}_\infty$ gain from the disturbances to the deviation of actual variables of interests from their nominal counterparts. The guar...

Learn-to-Fly (L2F) is a new framework that aims to replace the traditional iterative development paradigm for aerial vehicles with a combination of real-time aerodynamic modeling, guidance, and learning control. To ensure safe learning of the vehicle dynamics on the fly, this paper presents an $\mathcal{L}_1$ adaptive control ($\mathcal{L}_1$AC) ba...

Please check an extended version of this work at https://arxiv.org/abs/2112.01953. A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods try to obtain a fixed policy for all envisioned dynamic variation scenarios through r...

As a systematic method for gain-scheduling, the linear parameter-varying (LPV) system framework has been widely used for the design of aerospace control systems with large operating envelopes. This paper presents design and analysis of an adaptive control architecture for LPV systems subject to time-varying parametric uncertainties and external dis...

This paper presents a framework for the design and analysis of an $\mathcal{L}_1$ adaptive controller with a switching reference system. The use of a switching reference system allows the desired behavior to be scheduled across the operating envelope, which is often required in aerospace applications. The analysis uses a switched reference system t...

This paper presents a robust adaptive control solution for linear parameter-varying (LPV) systems with unknown input gain and unmatched nonlinear (state- and time-dependent) uncertainties based on the L1 adaptive control architecture and the idea of peak-to-peak gain (PPG) analysis/minimization from robust control. Specifically, we introduce new to...

This paper presents adaptive robust quadratic program (QP) based control using control Lyapunov and barrier functions for nonlinear systems subject to time-varying and state-dependent uncertainties. An adaptive estimation law is proposed to estimate the pointwise value of the uncertainties with pre-computable estimation error bounds. The estimated...

This paper validates a robust $H_\infty$ controller design method, experimentally, on miniaturized prototypes of the magnetically-actuated lens-tilting optical image stabilizers (OISs) with product variabilities. Five small-scale OIS prototypes with product variations are constructed by 3D printing. For the prototypes, the model parameters are iden...

This paper studies novel attack and defense strategies for multi-agent control systems. ZDA poses a formidable security challenge since its attack signal is hidden in the null-space of the state-space representation of the control system and hence it can evade conventional detection methods. In this paper, we propose realistic ZDA variations where...

We present L1-GP, an architecture based on L1 adaptive control and Gaussian Process Regression (GPR) for safe simultaneous control and learning. On one hand, the L1 adaptive control provides stability and transient performance guarantees, which allows for GPR to efficiently and safely learn the uncertain dynamics. On the other hand, the learned dyn...

This paper analyzes stealthy attacks, particularly the zero-dynamics attack (ZDA) in networked control systems. ZDA hides the attack signal in the null-space of the state-space representation of the control system and hence it cannot be detected via conventional detection methods. A natural defense strategy builds on changing the null-space via swi...

This paper studies novel attack and defense strategies, based on a class of stealthy attacks, namely the zero-dynamics attack (ZDA), for multi-agent control systems. ZDA poses a formidable security challenge since its attack signal is hidden in the null-space of the state-space representation of the control system and hence it can evade conventiona...

This paper presents a framework for design and analysis of an L1 adaptive controller with switching reference systems. Use of switching reference systems allows the desired behavior to be scheduled across the operating envelope, which is often required in aerospace applications. The analysis uses a switched reference system that assumes perfect kno...

This paper presents uncertainty modeling and robust controller design for 3 degrees-of-freedom miniaturized optical image stabilizers (OISs) against product variabilities. To develop a mathematical model of OISs with product variations, both model and uncertainty structures are determined by finite element analysis. The model parameters are identif...

This paper presents the design of multiple parameter-dependent robust controllers for mass-produced miniaturized optical image stabilizers (OIS’s), which are used to minimize the image blur in mobile devices caused by hand-induced camera shake. The dynamics of batch-fabricated OIS’s with inevitable product variations is represented by a set of line...

This paper presents a novel approach to designing switching linear parameter‐varying (SLPV) controllers with improved local performance and an algorithm for optimizing switching surfaces to further improve the performance of the SLPV controllers. The design approach utilizes the weighted average of the local L2‐gain bounds (representing the local p...

3D printing and moulding (3DPM) method is applied to the fabrication of a miniature magnetic actuator for optical image stabilization (OIS) applications. Polydimethylsiloxane (PDMS) and strontium ferrite (SrFe) nano powder are used as the main structural materials. Young’s modulus and the magnetization of the material with SrFe-doping ratios rangin...

This paper formulates and solves the problem of optimizing switching surfaces (SSs) in switching LPV (SLPV) controller design to further enhance the control performance. The conditions for the SLPV controller synthesis under fixed SSs are first presented, which involves a finite number of linear matrix inequalities. The SS design problem is then fo...

This paper addresses the problem of designing output-feedback switching linear parameter-varying (LPV) controllers under inexact measurement of scheduling parameters. The switching LPV controllers are robustly designed so that the stability and -gain performance of the switched closed-loop system can be guaranteed even under controller switching de...

This paper proposes an uncertainty modeling and robust controller design method for miniaturized 3 degrees-of-freedom OISs to deal with its product variabilities. A mathematical model of OISs with product variabilities is developed based on finite element analysis of uncertainties specific for this device. μ-synthesis technique is applied to the un...

In this paper, we deal with the problem of simultaneous design of state-feedback switching linear parameter-varying (LPV) controllers and switching surfaces for LPV plants to further improve the performance of the switching LPV controllers. The LPV plants that we consider have polynomially parameter-dependent state-space matrices. Using slack varia...

This paper presents robust control of large-scale prototypes for miniaturized optical image stabilizers (OIS's) with product variations. Based on the conceptual design of a miniaturized lens-tilting OIS for mobile applications, large-scale 3-DOF prototypes are fabricated as a proof of concept. Variations in geometrical parameter of the lens platfor...

Passive torque servo system (PTSS) simulates aerodynamic load and exerts the load on actuation system, but PTSS endures position coupling disturbance from active motion of actuation system, and this inherent disturbance is called extra torque. The most important issue for PTSS controller design is how to eliminate the influence of extra torque. Usi...

This paper presents a parameter identification method with nonlinear ordinary differential equation (ODE) model for electro-hydraulic servo systems (EHSS) based on Matlab toolbox, in which the values of known parameters are fixed and the values of unknown parameters are identified. In order to avoid the problem of over-parameterization, this paper...

Aiming at the problems of vibration on hydraulic pipe in aircraft, using math modeling and simulation is a quite efficient and effective method in theory. In this paper, the 14- equation Fluid-Structure Interaction (FSI) with influence of viscous friction is established for modeling the pipe and fluid. By using the Transfer Matrix Method (TMM), the...