检索结果-南通市图书馆

Constrained reinforcement learning with statewise projection: a control barrier function approach

Science China(Information Sciences) 2024年第3期67卷 136-154页

作者： Xinze JIN Kuo LI Qingshan JIA Department of Automation Tsinghua University

Safety is a critical issue for reinforcement learning(RL), as it may be risky for some actual applications if the learning process involves unsafe exploration. Instead of formulating constraints as expectationbased in constrained RL, considering statewise safety in constrained RL is more meaningful. This work aims to address the issue of safe projection in RL by introducing a control barrier function that inherently learns a safe policy through a set certificate. We seek to analyze some theoretical properties of safe projection in the learning process, including convergence and performance bound, and extend the discussion into ensembles and guided controllers. Moreover, we approach analytical solutions for deterministic and stochastic system dynamics. Experimental results in different tasks show that the proposed method achieves better effects in terms of both performance and safety.

关键词： reinforcement learning safe projection control barrier function

来源：

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Multi-agent system motion planning under temporal logic specifications and control barrier function

引用

control Theory and Technology 2020年第3期18卷 269-278页

作者： Xinyuan HUANG Li LI Jie CHEN College of Electronics and Information Engineering Tongji UniversityShanghai 201804China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai 201210China

In this paper,w e provide a novel scheme to solve the motion planning problem of multi-agent systems under high-level task ***,linear temporal logic is applied to express the global task *** an efficient and decentralized algorithm is proposed to decom pose it into local tasks.M oreover,w e use control barrier function to synthesize the local controller for each agent under the linear temporal logic motion plan with safety ***,simulation results show the effectiveness and efficiency of our proposed scheme.

关键词： Temporal logic multi-agent system formal methods control barrier function

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A novel kind of sufficient conditions for safety judgement based on control barrier function

引用

Science China(Information Sciences) 2021年第9期64卷 264-266页

作者： Zheren ZHU Yi CHAI Zhimin YANG Key Laboratory of Complex System Safety and control (Chongqing University) Ministry of Education School of Automation Chongqing University

Dear editor,Recently, work safety accidents have started to occur on a large scale in Chinese petrochemical companies. Further,the operational safety of large and complex systems is being closely monitored by our government, environmental organizations,and conscientious citizens. The scale of complex systems, such as industrial systems and smart grids,

关键词： safety criterion control barrier function fault safety complex system sufficient condition

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Multi-agent System Motion Planning under Temporal Logic Specifications and control barrier function

Multi-agent System Motion Planning under Temporal Logic Spec...

引用

第三十九届中国控制会议

作者： Xinyuan Huang Li Li Jie Chen IEEE IFAC Chinese Academy of Engineering Tongji University the State Key Laboratory of Intelligent control and Decision of Complex Systems the Chinese Association of Automation the Chinese Artificial Intelligence Society College of Electronics and Information Engineering Tongji University Shanghai Reserach Institute for Intelligent Autonomous Systems

In this paper, we provide a novel scheme to solve the motion planning problem of multi-agent systems under highlevel task specifications. First, linear temporal logic is applied to express the global task specification. Then an efficient and decentralization algorithm is proposed to decompose it into local tasks. Finally, we use control barrier function to synthesize the local controller for each agent under the LTL motion plan safety constraint. Simulation results prove the effectiveness and efficiency of our proposed method.

关键词： temporal logic multi-agent system formal methods control barrier function

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Safety-Critical Optimal control for Autonomous Systems

引用

Journal of Systems Science & Complexity 2021年第5期34卷 1723-1742页

作者： XIAO Wei CASSANDRAS G.Christos BELTA Calin Division of Systems Engineering and Center for Information and Systems Engineering Boston UniversityBrooklineMA 02446USA

This paper presents an overview of the state of the art for safety-critical optimal control of autonomous *** control methods are well studied,but become computationally infeasible for real-time applications when there are multiple hard safety constraints *** guarantee such safety constraints,it has been shown that optimizing quadratic costs while stabilizing affine control systems to desired(sets of)states subject to state and control constraints can be reduced to a sequence of Quadratic Programs(QPs)by using control barrier functions(CBFs)and control Lyapunov functions(CLFs).The CBF method is computationally efficient,and can easily guarantee the satisfaction of nonlinear constraints for nonlinear systems,but its wide applicability still faces several ***,safety is hard to guarantee for systems with high relative degree,and the above mentioned QPs can easily be infeasible if tight or time-varying control bounds are *** resulting solution is also sub-optimal due to its myopic solving ***,this method works conditioned on the system dynamics being accurately *** authors discuss recent solutions to these issues and then present a framework that combines Optimal control with CBFs,hence termed OCBF,to obtain near-optimal solutions while guaranteeing safety constraints even in the presence of noisy *** application of the OCBF approach is included for autonomous vehicles in traffic networks.

关键词： control barrier function optimal control safety

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

洋流干扰下无人船限制水域直线跟踪安全视距制导

引用

哈尔滨工程大学学报（英文版） 2023年第3期22卷 602-613页

作者：彭周华李建众韩冰古楠 School of Marine Electrical Engineering Dalian Maritime UniversityDalian 116026China Dalian Key Laboratory of Swarm control and Electrical Technology for Intelligent Ships Dalian 116026China Shanghai Ship and Shipping Research Institute Co.Ltd. Shanghai 200135China National Engineering Research Center of Ship&Shipping control System Shanghai 200135China

The collision-free straight-line following of an unmanned surface vehicle(USV)moving in a constrained water region subject to stationary and moving obstacles is addressed in this *** systems are normally subjected to surge velocity constraints,yaw rate constraints,and unknown ocean ***,a safety-certificated line-of-sight(LOS)guidance method is proposed to achieve a constrained straight-line following ***,an antidisturbance LOS guidance law is designed based on the LOS guidance scheme and an extended state ***,collision avoidance with waterway boundaries and stationary/moving obstacles is encoded in control barrier functions,utilizing which the safety constraints are transformed into input ***,safety-certificated guidance signals are obtained by solving a quadratic programming problem subject to input *** the proposed safety-certified LOS guidance method,the USV can accomplish a straight-line following task with guaranteed input-to-state *** results substantiate the efficacy of the proposed safety-certificated LOS guidance method for the straight-line following of USVs moving in a constrained water region subject to unknown ocean currents.

关键词： Line-of-sight guidance Constrained water region Unmanned surface vehicle control barrier function Extended state observer

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：