Sampling-guided symbolic control framework under changing environments

变化环境下采样引导的符号控制框架

• 批准号: 21K14191
• 负责人: プルエクプラサート サシニー
• 金额: $ 1.83万
• 依托单位: National Institute of Advanced Industrial Science and Technology (2022)National Institute of Informatics (2021)
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Early-Career Scientists
• 财政年份: 2021
• 资助国家: 日本
• 起止时间: 2021-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-21K14191/
• 关键词: symbolic control; motion planning; robotics; control theory; temporal logic

During this academic year, there were two main research directions of the project.1. The first direction is to extend the developed symbolic control framework to control and monitor multi-agent systems, focusing on nonholonomic robots.2. The second direction is to study a safe learning approach using discrete (symbolic) structures.

在本学年，项目主要有两个研究方向。第一个方向是扩展已开发的符号控制框架，以控制和监视多智能体系统，重点是非完整机器人。第二个方向是研究使用离散（符号）结构的安全学习方法。

项目成果

Logic for Timed Agent Network Topologies

定时代理网络拓扑的逻辑

• 发表时间: 2022
• 作者: C. Eberhart;J. Haydon;J. Dubut;A. Cetinkaya;S. Pruekprasert
• 通讯作者: S. Pruekprasert

Dynamic Shielding for Reinforcement Learning in Black-Box Environments

黑盒环境中强化学习的动态屏蔽

• DOI: 10.1007/978-3-031-19992-9_2
• 发表时间: 2022
• 期刊: Lecture Notes in Computer Science
• 作者: Waga Masaki;Castellano Ezequiel;Pruekprasert Sasinee;Klikovits Stefan;Takisaka Toru;Hasuo Ichiro
• 通讯作者: Hasuo Ichiro

Fast Synthesis for Symbolic Self-triggered Control under Right-recursive LTL Specifications

• DOI: 10.1109/cdc45484.2021.9683328
• 发表时间: 2021-03
• 期刊: 2021 60th IEEE Conference on Decision and Control (CDC)
• 作者: Sasinee Pruekprasert;Clovis Eberhart;Jérémy Dubut

Local Opacity Verification for Distributed Discrete Event Systems

• DOI: 10.1109/cdc45484.2021.9683017
• 发表时间: 2021-12
• 期刊: 2021 60th IEEE Conference on Decision and Control (CDC)
• 作者: Sasinee Pruekprasert;Kai Cai