使用数据驱动的预测控制的安全强化学习

Mahmoud Selim, Amr Alanwar, M. El-Kharashi, Hazem Abbas, K. Johansson
{"title":"使用数据驱动的预测控制的安全强化学习","authors":"Mahmoud Selim, Amr Alanwar, M. El-Kharashi, Hazem Abbas, K. Johansson","doi":"10.1109/ICCSPA55860.2022.10018994","DOIUrl":null,"url":null,"abstract":"Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the exploration nature of many RL algorithms, especially when the model of the robot and the environment are unknown. To address this challenge, we propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer uses a data-driven predictive controller to enforce safety guarantees for RL policies during training and after deployment. The RL agent proposes an action that is verified by computing the data-driven reachability analysis. If there is an intersection between the reachable set of the robot using the proposed action, we call the data-driven predictive controller to find the closest safe action to the proposed unsafe action. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In the simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem for a Turtlebot 3 in Gazebo and a quadrotor in Unreal Engine 4 (UE4).","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Safe Reinforcement Learning using Data-Driven Predictive Control\",\"authors\":\"Mahmoud Selim, Amr Alanwar, M. El-Kharashi, Hazem Abbas, K. Johansson\",\"doi\":\"10.1109/ICCSPA55860.2022.10018994\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the exploration nature of many RL algorithms, especially when the model of the robot and the environment are unknown. To address this challenge, we propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer uses a data-driven predictive controller to enforce safety guarantees for RL policies during training and after deployment. The RL agent proposes an action that is verified by computing the data-driven reachability analysis. If there is an intersection between the reachable set of the robot using the proposed action, we call the data-driven predictive controller to find the closest safe action to the proposed unsafe action. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In the simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem for a Turtlebot 3 in Gazebo and a quadrotor in Unreal Engine 4 (UE4).\",\"PeriodicalId\":106639,\"journal\":{\"name\":\"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCSPA55860.2022.10018994\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCSPA55860.2022.10018994","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

强化学习(RL)算法可以在决策和连续控制任务中达到最先进的性能。然而,由于许多强化学习算法的探索性质,特别是在机器人模型和环境未知的情况下,在安全关键系统上应用强化学习算法仍然需要充分的理由。为了应对这一挑战,我们提出了一个数据驱动的安全层,作为不安全操作的过滤器。安全层使用数据驱动的预测控制器在训练期间和部署后对RL策略实施安全保证。RL代理提出一个操作,该操作通过计算数据驱动的可达性分析来验证。如果使用建议动作的机器人的可达集合之间存在交集,我们调用数据驱动的预测控制器来找到与建议的不安全动作最近的安全动作。如果提议的操作不安全,安全层会惩罚RL代理,并用最接近的安全操作替换它。在模拟中,我们表明我们的方法优于最先进的安全RL方法在Gazebo中的Turtlebot 3和虚幻引擎4 (UE4)中的四旋翼机器人导航问题上。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Safe Reinforcement Learning using Data-Driven Predictive Control
Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the exploration nature of many RL algorithms, especially when the model of the robot and the environment are unknown. To address this challenge, we propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer uses a data-driven predictive controller to enforce safety guarantees for RL policies during training and after deployment. The RL agent proposes an action that is verified by computing the data-driven reachability analysis. If there is an intersection between the reachable set of the robot using the proposed action, we call the data-driven predictive controller to find the closest safe action to the proposed unsafe action. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In the simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem for a Turtlebot 3 in Gazebo and a quadrotor in Unreal Engine 4 (UE4).
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信