In recent years, reinforcement learning techniques have gained widespread application in control synthesis. However, in the context of safety-critical systems, employing trial-and-error based reinforcement learning ma...
详细信息
ISBN:
(数字)9798350354409
ISBN:
(纸本)9798350354416
In recent years, reinforcement learning techniques have gained widespread application in control synthesis. However, in the context of safety-critical systems, employing trial-and-error based reinforcement learning may be unacceptable due to the potential risks it poses during the learning process. Consequently, the development of safe reinforcement learning techniques has become imperative. This paper addresses the challenge of safe reinforcement learning for controller synthesis, particularly when safety specifications are intricately linked to the real-time behavior of the system. To articulate time-sensitive requirements, we leverage Metric Interval Temporal Logic (MITL). To ensure safety throughout the learning process, we introduce an additional reactive controller called a shield. Specifically, the shield functions to reject any behavior that violates the real-time specifications, thus mitigating potential risks. The efficacy of our proposed approach is demonstrated through simulation results, highlighting its ability to satisfy safety constraints in the dynamic environment of controller synthesis.
This paper proposes a novel online-learning-enabled hierarchical distributionally robust energy management framework for multi-microgrids (MMGs) with off-site hydrogen refueling stations (HRSs). The proposed framework...
详细信息
作者：
Xu, RuijieChen, ShichaoSun, WenqiaoLv, YishengLuo, JialiangTang, YingInstitute of Automation
Chinese Academy of Sciences College of Information Science & Technology Beijing University of Chemical Technology The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Institute of Automation
Chinese Academy of Sciences The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Transportation and Economics Research Institute
The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China Institute of Automation
Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Institute of Automation
Chinese Academy of Sciences China University of Geosciences Beijing School of Information Engineering The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Rowan University
Department of Electrical and Computer Engineering Glassboro United States
Global Navigation Satellite systems (GNSS) can provide real-time positioning information for outdoor users, but cannot for indoor scenarios or heavily occluded outdoor scenarios. Strap-down Inertial Navigation system ...
详细信息
In generalized Nash equilibrium(GNE)seeking problems over physical networks such as power grids,the enforcement of network constraints and time-varying environment may bring high computational *** online algorithms is...
详细信息
In generalized Nash equilibrium(GNE)seeking problems over physical networks such as power grids,the enforcement of network constraints and time-varying environment may bring high computational *** online algorithms is recognized as a promising method to cope with this challenge,where the task of computing system states is replaced by directly using measured values from the physical *** this paper,we propose an online distributed algorithm via measurement feedback to track the GNE in a time-varying networked resource sharing *** that some system states are not measurable and measurement noise always exists,a dynamic state estimator is incorporated based on a Kalman filter,rendering a closed-loop dynamics of measurement-feedback driven online *** prove that,with a fixed step size,this online algorithm converges to a neighborhood of the GNE in *** simulations validate the theoretical results.
Electric vehicles (EVs) have experienced an unprecedented increase in their penetration; in well developed countries; due to the advancement of battery technology and the need to make transportation more environmental...
Electric vehicles (EVs) have experienced an unprecedented increase in their penetration; in well developed countries; due to the advancement of battery technology and the need to make transportation more environmentally friendly. As a result of this trend, EVs have become an integral part of those countries power grid ecosystem, where they may be used as both a source, and a consumer of energy. However, cybersecurity risks associated with large fleets of EVs within the power grids can significantly impact the normal operation of distribution systems. This paper considers the cyber-attack consequences, from attackers’ perspective. The cyber attackers under study target the charging price (CP) by increasing the CP in off-peak hours and accordingly subsiding it in on-peak hours. A two-stage optimization framework is proposed to identify the most important ultra-fast charging stations (XFCs) under the cyber-attack, meanwhile, the EV users’ response to the compromised CP is considered. Then, the proposed model is implemented on a modified IEEE 123-bus distribution test system, and the effectiveness of the model is proved through some case studies. In particular, they demonstrated that the amount of load shedding is increased by 8.198 MW when the EV user response is taken into account.
This paper presents an event-based asymptotic tracking control scheme designed for strict feedback systems with unknown control directions. The control directions directly determine how the controller acts on the syst...
详细信息
ISBN:
(数字)9789887581598
ISBN:
(纸本)9798331540845
This paper presents an event-based asymptotic tracking control scheme designed for strict feedback systems with unknown control directions. The control directions directly determine how the controller acts on the system, thus impacting the system's stability and convergence speed. When the control directions are unknown, it presents a significant challenge in controller design. To tackle this issue, the Nussbaum-type gains are introduced. However, this method increases communication overhead. Hence, an event-triggered mechanism is introduced to alleviate this burden. Additionally, to achieve and maintain desired target states, satisfying control requirements and performance demands, this paper improves the event-triggered mechanism to achieve asymptotic tracking. Finally, the feasibility and effectiveness of the proposed design are validated through a simulation example.
We investigate a pursuit-evasion game taking place in an unbounded three-dimensional space, where a flexible pursuer with hybrid dynamics collaborates with a fast pursuer and aims to capture a flexible evader within a...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
We investigate a pursuit-evasion game taking place in an unbounded three-dimensional space, where a flexible pursuer with hybrid dynamics collaborates with a fast pursuer and aims to capture a flexible evader within a finite time. The key feature of this problem lies in the hybrid dynamics of the flexible pursuer, which can change its dynamics once during the game and switch to a fast pursuer with increased speed but lower maneuverability. To address this challenge, we devise a hybrid strategy based on the soft actor-critic framework, tailored specifically for the flexible pursuer, which encompasses both maneuvering and switch tactics. We introduce a switch factor to the input of the actor network and incorporate switch actions to further expand the action space. These additions enable the flexible pursuer to execute maneuvering actions and determine a moment to switch to a fast pursuer. The reward function is designed to account for related angle, altitude, speed, and sparse reward. Through extensive ablation experiments conducted in a simulated environment, we demonstrate the efficacy of our algorithm in facilitating the learning of hybrid strategies for the flexible pursuer, resulting in significantly improved capture rates compared to alternative methods.
Existing studies on large-signal synchronization stability of the grid-following voltage-source converters (VSCs) have been focused on the phase-locked loop (PLL). Saturation nonlinearities introduced by current or vo...
详细信息
Aiming at the task planning problem of multi-robot under linear temporal logic(LTL), this paper proposes an improved sampling planning algorithm based on Nondeterministic Büchi automaton(NBA) guidance. Firstly, t...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
Aiming at the task planning problem of multi-robot under linear temporal logic(LTL), this paper proposes an improved sampling planning algorithm based on Nondeterministic Büchi automaton(NBA) guidance. Firstly, this paper defines a kind of LTL task planning problem, which mainly focuses on the meaningful key nodes in the task execution of each robot, and there are many sequential dependencies of task constraints. Then, an improved sampling algorithm framework is proposed,which uses a more efficient way to build a search tree and reduces the number of nodes in the tree. Furthermore, the sampling points are guided by NBA to ensure that sampling is conducive to the advancement of time-series tasks. And considering the task feasible region of each robot, the auction algorithm is introduced to optimize the local matching relationship, which greatly improves the quality of sampling points. Finally, numerical simulation is carried out to solve the LTL task planning problem. The optimality and stability of the algorithm are obviously improved, and the time consumption of this algorithm is obviously better than that of the existing advanced algorithms.
The security of mobile robotic networks (MRNs) has been an active research topic in recent years. This paper aims to secure the ubiquitous formation control of MRNs against the replacement attack, where an external ro...
详细信息
暂无评论