More Like this

1. L1 adaptive control with Bayesian learning. In Learning for Dynamics and Control

   Gahlawat, A. (July 2020, Machine learning research)

   null (Ed.)

   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 dynamics can be conveniently incorporated into the L1 control architecture without sacrificing robustness and tracking performance. Subsequently, the learned dynamics can lead to less conservative designs for performance/robustness tradeoff. We illustrate the efficacy of the proposed architecture via numerical simulations. 

   more » « less
2. ROBUST MODEL BASED REINFORCEMENT LEARNING USING L1 ADAPTIVE CONTROL

   Sung, Minjun; Karumanchi, Sambhu_Harimanas; Gahlawat, Aditya; Hovakimyan, Naira (January 2024, International Conference on learning representations, openreview.net)

   We introduce L1-MBRL, a control-theoretic augmentation scheme for Model-Based Reinforcement Learning (MBRL) algorithms. Unlike model-free approaches, MBRL algorithms learn a model of the transition function using data and use it to design a control input. Our approach generates a series of approximate control-affine models of the learned transition function according to the proposed switching law. Using the approximate model, control input produced by the underlying MBRL is perturbed by the L1 adaptive control, which is designed to enhance the robustness of the system against uncertainties. Importantly, this approach is agnostic to the choice of MBRL algorithm, enabling the use of the scheme with various MBRL algorithms. MBRL algorithms with L1 augmentation exhibit enhanced performance and sample efficiency across multiple MuJoCo environments, outperforming the original MBRL algorithms, both with and without system noise. 

   more » « less
3. Improving the Robustness of Reinforcement Learning Policies With L1 Adaptive Control

   Yikun Cheng, Pan Zhao (July 2022, IEEE robotics automation letters)

   Tamim Asfour, editor in (Ed.)

   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 L1 adaptive controller (L1AC). Leveraging the capability of an L1AC for fast estimation and active ompensation of dynamic variations, the proposed approach can improve the robustness of an RL policy which is trained either in a simulator or in the real world without consideration of a broad class of dynamic variations. Numerical and real-world experiments empirically demonstrate the efficacy of the proposed approach in robustifying RL policies trained using both model-free and modelbased methods. 

   more » « less
4. A Multirate Adaptive Control for MIMO Systems with Application to Cyber-Physical Security

   https://doi.org/10.1109/CDC.2018.8619570  

   Jafarnejadsani, Hamidreza; Lee, Hanmin; Hovakimyan, Naira; Voulgaris, Petros (December 2018, 2018 IEEE Conference on Decision and Control)

   This paper proposes a multirate output-feedback controller for multi-input multi-output (MIMO) systems, possibly with non-minimum-phase zeros, using the L1 adaptive control structure. The analysis of stability and robustness of the sampled-data controller reveals that under certain conditions the performance of a continuous-time reference system is uniformly recovered as the sampling time goes to zero. The controller is designed for detection and mitigation of actuator attacks. By considering a multirate formulation, stealthy zero-dynamics attacks become detectable. The experimental results from the flight test of a small quadrotor are provided. The tests show that the multirate L1 controller can effectively detect the zero-dynamics actuator attack and recover stability of the quadrotor. 

   more » « less
5. Contraction L1-Adaptive Control using Gaussian Processes. In Learning for Dynamics and Control

   Gahlawat, A. (January 2021, Proceedings of Machine Learning Research)

   null (Ed.)

   We present a control framework that enables safe simultaneous learning and control for systems subject to uncertainties. The two main constituents are contraction theory-based L1-adaptive (CL1) control and Bayesian learning in the form of Gaussian process (GP) regression. The CL1 controller ensures that control objectives are met while providing safety certificates. Furthermore, the controller incorporates any available data into GP models of uncertainties, which improves performance and enables the motion planner to achieve optimality safely. This way, the safe operation of the system is always guaranteed, even during the learning transients. Keywords: Safe Learning, Planning, Adaptive Control, Gaussian Process Regression 

   more » « less