CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control

IF 4.6 2区 计算机科学 Q2 ROBOTICS
Se Hwan Jeon;Seungwoo Hong;Ho Jae Lee;Charles Khazoom;Sangbae Kim
{"title":"CusADi: A GPU Parallelization Framework for Symbolic Expressions and Optimal Control","authors":"Se Hwan Jeon;Seungwoo Hong;Ho Jae Lee;Charles Khazoom;Sangbae Kim","doi":"10.1109/LRA.2024.3512254","DOIUrl":null,"url":null,"abstract":"The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of formulating and solving optimization problems across thousands of instances. In this work, we present \n<monospace>CusADi</monospace>\n, an extension of the \n<monospace>casadi</monospace>\n symbolic framework to support the parallelization of arbitrary closed-form expressions on GPUs with \n<monospace>CUDA</monospace>\n. We also formulate a closed-form approximation for solving general optimal control problems, enabling large-scale parallelization and evaluation of MPC controllers. Our results show a ten-fold speedup relative to similar MPC implementation on the CPU, and we demonstrate the use of \n<monospace>CusADi</monospace>\n for various applications, including parallel simulation, parameter sweeps, and policy training.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 2","pages":"899-906"},"PeriodicalIF":4.6000,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Robotics and Automation Letters","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10778410/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ROBOTICS","Score":null,"Total":0}
引用次数: 0

Abstract

The parallelism afforded by GPUs presents significant advantages in training controllers through reinforcement learning (RL). However, integrating model-based optimization into this process remains challenging due to the complexity of formulating and solving optimization problems across thousands of instances. In this work, we present CusADi , an extension of the casadi symbolic framework to support the parallelization of arbitrary closed-form expressions on GPUs with CUDA . We also formulate a closed-form approximation for solving general optimal control problems, enabling large-scale parallelization and evaluation of MPC controllers. Our results show a ten-fold speedup relative to similar MPC implementation on the CPU, and we demonstrate the use of CusADi for various applications, including parallel simulation, parameter sweeps, and policy training.
一个用于符号表达式和最优控制的GPU并行化框架
gpu提供的并行性在通过强化学习(RL)训练控制器方面具有显著的优势。然而,将基于模型的优化集成到此过程中仍然具有挑战性,因为在数千个实例中制定和解决优化问题非常复杂。在这项工作中,我们提出了CusADi, casadi符号框架的扩展,以支持CUDA gpu上任意封闭形式表达式的并行化。我们还为解决一般最优控制问题制定了一个封闭形式的近似,使MPC控制器的大规模并行化和评估成为可能。我们的结果显示,相对于在CPU上实现类似的MPC, CusADi的速度提高了10倍,并且我们演示了在各种应用程序中使用CusADi,包括并行模拟、参数扫描和策略训练。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Robotics and Automation Letters
IEEE Robotics and Automation Letters Computer Science-Computer Science Applications
CiteScore
9.60
自引率
15.40%
发文量
1428
期刊介绍: The scope of this journal is to publish peer-reviewed articles that provide a timely and concise account of innovative research ideas and application results, reporting significant theoretical findings and application case studies in areas of robotics and automation.
×
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