In this article, we consider the problem of optimally augmenting an actuator redundant system with additional actuators, so that the energy required to meet a given control objective is minimized. We study this actuat...
详细信息
In this article, we consider the problem of optimally augmenting an actuator redundant system with additional actuators, so that the energy required to meet a given control objective is minimized. We study this actuator selection problem in two distinct cases;first, in the case where the control objective of the system is not known a priori, and second, in the case where the control objective is a linear state-feedback control law. In the latter scenario, knowledge of the system's state and input matrices is required to solve the corresponding actuator selection problem. However, we relax this requirement by exploiting trajectory data gathered from the system, and using them to iteratively approximate the antistabilizing solution of an associated algebraic Riccati equation (ARE). Notably, the proposed iterative procedure is proved to be small-disturbance input-to-state stable even though the ARE associated with it entails no strictly positive-definite constant term;a result that significantly extends prior work. Finally, to further exploit the obtained trajectory data, we show that these can be used to perform online actuator fault detection without knowledge of the system's matrices, and with complexity lower than that of existing methods. Simulations showcase the theoretical findings.
Collision-free navigation is a critical issue in robotic systems as the environment is often dynamic and uncertain. This paper investigates a data-stream-driven motion control problem for mobile robots to avoid random...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Collision-free navigation is a critical issue in robotic systems as the environment is often dynamic and uncertain. This paper investigates a data-stream-driven motion control problem for mobile robots to avoid randomly moving obstacles when the probability distribution of the obstacle's movement is partially observable through data and can be even time-varying. A data-stream-driven ambiguity set is firstly constructed from movement data by leveraging a Dirichlet process mixture model and is updated online using real-time data. Then we propose an Online-learning-based Distributionally Robust Nonlinear Model Predictive control (OL-DR-NMPC) approach for limiting the risk of collision through considering the worst-case distribution within the ambiguity set. To facilitate solving the OL-DR-NMPC problem, we reformulate it as a finite-dimensional nonlinear optimization problem. To cope with the bilinear matrix inequality constraints in the nonlinear problem, we develop a parabolic relaxation and a sequential algorithm, by which the problem is further transformed into polynomial-time solvable surrogates. The simulations using a quadrotor model are employed to demonstrate the effectiveness and advantages of the proposed method.
The modern power grid is witnessing a shift in operations from traditional control methods to more advanced operational mechanisms. Due to the nonconvex nature of the Alternating Current Optimal Power Flow (ACOPF) pro...
详细信息
ISBN:
(纸本)9798350318562;9798350318555
The modern power grid is witnessing a shift in operations from traditional control methods to more advanced operational mechanisms. Due to the nonconvex nature of the Alternating Current Optimal Power Flow (ACOPF) problem and the need for operations with better granularity in the modern smart grid, system operators require a more efficient and reliable ACOPF solver. While data-driven ACOPF methods excel in directly inferring the optimal solution based on power grid demand, achieving both feasibility and optimality remains a challenge due to the NP-hardness of the problem. In this paper, we propose a physics-informed machine learning model and a feasibility calibration algorithm to produce solutions for the ACOPF problem. Notably, the machine learning model produces solutions with a 0.5% and 1.4% optimality gap for ieee bus 14 and 118 grids, respectively. The feasibility correction algorithm converges for all test scenarios on bus 14 and achieves a 92.2% convergence rate on bus 118.
In this paper, the data-driven optimal control problem is studied for continuous-time linear nonzero-sum games. Two kinds of reinforcement learning algorithms, i.e., reinforcement learning algorithm with data-storage ...
详细信息
ISBN:
(纸本)9798331518509;9798331518493
In this paper, the data-driven optimal control problem is studied for continuous-time linear nonzero-sum games. Two kinds of reinforcement learning algorithms, i.e., reinforcement learning algorithm with data-storage based least-square method and reinforcement learning algorithm with filter based least-square method, are presented to obtain the Nash equilibrium solution. The properties of the presented reinforcement learning algorithms are analyzed. Simulation results show the efficiency of the presented reinforcement learning algorithms.
Many adverse events during laparoscopic cholecystectomy surgery occur due to errors in visual perception and judgment by surgeons, leading to misunderstandings of anatomical structures, particularly in surgeries perfo...
详细信息
With the rapid development of integrated energy system (IES), the combine operation of heterogeneous energy networks becomes richer and richer, and the nonlinear characteristics of the multi-energy flow (MEF) model be...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
With the rapid development of integrated energy system (IES), the combine operation of heterogeneous energy networks becomes richer and richer, and the nonlinear characteristics of the multi-energy flow (MEF) model become more and more significant, which poses a challenge to the analysis and optimization of system operation. In this paper, a joint driven MEF modeling method based on electricity-heat interconnected system is proposed, which utilizes a deep learning method to mine the internal relationship of MEF historical data and effectively avoids the stability problem caused by iterative. On this basis, the fusion mechanism-driven module is used as a buffer zone for the nonlinear regression process of MEF to reduce the error stacking. This model can achieve the organic unification of calculation accuracy and timeliness to a certain extent. Finally, different scales of electricity-heat interconnection systems are selected for example analysis to verify the accuracy and implementation of the proposed method.
Machine learning technologies have become an invaluable solution to operating mobile networks efficiently. In particular, multi-agent reinforcement learning (MARL) enables the learning of policies to sleep base statio...
详细信息
ISBN:
(纸本)9798350387414
Machine learning technologies have become an invaluable solution to operating mobile networks efficiently. In particular, multi-agent reinforcement learning (MARL) enables the learning of policies to sleep base stations (BSs) located in a broad range of areas cooperatively for energy saving in network operation. However, if the policies of agents are trained on an inaccurate simulation environment in MARL, their performance may be compromised when deployed in the real environment. In this paper, we propose a practical learning approach to obtain policies for BS sleep control via MARL with data-driven radio environment map (REM) calibration. In this approach, we first train REM calibration models as residual models using actual received power data collected in advance. By leveraging these data-driven calibration models in conjunction with statistical pathloss models provided by 3GPP, our network simulator accurately replicates the intensity of signals from BSs in accordance with the real environment. We then train policies for BS sleep control on the calibrated network simulator using an extended constrained policy optimization algorithm for MARL that explicitly deals with constraint satisfaction on costs in addition to reward maximization. Numerical experiments demonstrate that the BS sleep control with the policies derived from our learning approach achieves both reducing power consumption of BSs and guaranteeing quality of service (QoS) in network operation without performance degradation upon *** learning technologies have become an invaluable solution to operating mobile networks efficiently. In particular, multi-agent reinforcement learning (MARL) enables the learning of policies to sleep base stations (BSs) located in a broad range of areas cooperatively for energy saving in network operation. However, if the policies of agents are trained on an inaccurate simulation environment in MARL, their performance may be compromised when deployed in the
There are two major challenges for scaling up robot navigation around dynamic obstacles: the complex interaction dynamics of the obstacles can be hard to model analytically, and the complexity of planning and control ...
详细信息
ISBN:
(纸本)9781665491907
There are two major challenges for scaling up robot navigation around dynamic obstacles: the complex interaction dynamics of the obstacles can be hard to model analytically, and the complexity of planning and control grows exponentially in the number of obstacles. data-driven and learning-based methods are thus particularly valuable in this context. However, data-driven methods are sensitive to distribution drift, making it hard to train and generalize learned models across different obstacle densities. We propose a novel method for compositional learning of Sequential Neural control Barrier models (SN-CBFs) to achieve scalability. Our approach exploits an important observation: the spatial interaction patterns of multiple dynamic obstacles can be decomposed and predicted through temporal sequences of states for each obstacle. Through decomposition, we can generalize control policies trained only with a small number of obstacles, to environments where the obstacle density can be 100x higher. We demonstrate the benefits of the proposed methods in improving dynamic collision avoidance in comparison with existing methods including potential fields, end-to-end reinforcement learning, and model-predictive control. We also perform hardware experiments and show the practical effectiveness of the approach in the supplementary video.
This paper investigates the model-free adaptive fault-tolerant constrained control problem of cyber-physical systems (CPSs) under denial-of-service (DoS) attacks. Firstly, the compact form dynamic linearization (CFDL)...
详细信息
In this work, a novel online model-free controller for an underactuated dirigible is developed based on reinforcement learning and optimal control theory. A reinforcement learning structure is used while overcoming th...
详细信息
ISBN:
(纸本)9781665491907
In this work, a novel online model-free controller for an underactuated dirigible is developed based on reinforcement learning and optimal control theory. A reinforcement learning structure is used while overcoming the dependence of the value function on future values by introducing a neural network that is adapted using input-output data. The suboptimal critic neural network is structured such that optimality is guaranteed over the interval from which the data is valid. The system performance is validated using a highly realistic physics engine, Gazebo, with the robot operating system (ROS) interface and the results are compared to the performance of a model-based controller specifically designed to control the airship model. It is emphasized that the proposed formulation does not leverage any knowledge of vehicle dynamics and thus is considered a vehicle agnostic control strategy.
暂无评论