从作为概率自动机的演示中学习任务规范

Mattijs Baert, Sam Leroux, Pieter Simoens
{"title":"从作为概率自动机的演示中学习任务规范","authors":"Mattijs Baert, Sam Leroux, Pieter Simoens","doi":"arxiv-2409.07091","DOIUrl":null,"url":null,"abstract":"Specifying tasks for robotic systems traditionally requires coding expertise,\ndeep domain knowledge, and significant time investment. While learning from\ndemonstration offers a promising alternative, existing methods often struggle\nwith tasks of longer horizons. To address this limitation, we introduce a\ncomputationally efficient approach for learning probabilistic deterministic\nfinite automata (PDFA) that capture task structures and expert preferences\ndirectly from demonstrations. Our approach infers sub-goals and their temporal\ndependencies, producing an interpretable task specification that domain experts\ncan easily understand and adjust. We validate our method through experiments\ninvolving object manipulation tasks, showcasing how our method enables a robot\narm to effectively replicate diverse expert strategies while adapting to\nchanging conditions.","PeriodicalId":501031,"journal":{"name":"arXiv - CS - Robotics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learning Task Specifications from Demonstrations as Probabilistic Automata\",\"authors\":\"Mattijs Baert, Sam Leroux, Pieter Simoens\",\"doi\":\"arxiv-2409.07091\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Specifying tasks for robotic systems traditionally requires coding expertise,\\ndeep domain knowledge, and significant time investment. While learning from\\ndemonstration offers a promising alternative, existing methods often struggle\\nwith tasks of longer horizons. To address this limitation, we introduce a\\ncomputationally efficient approach for learning probabilistic deterministic\\nfinite automata (PDFA) that capture task structures and expert preferences\\ndirectly from demonstrations. Our approach infers sub-goals and their temporal\\ndependencies, producing an interpretable task specification that domain experts\\ncan easily understand and adjust. We validate our method through experiments\\ninvolving object manipulation tasks, showcasing how our method enables a robot\\narm to effectively replicate diverse expert strategies while adapting to\\nchanging conditions.\",\"PeriodicalId\":501031,\"journal\":{\"name\":\"arXiv - CS - Robotics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Robotics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07091\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07091","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

传统上,为机器人系统指定任务需要专业的编码技术、深厚的领域知识和大量的时间投入。虽然从演示中学习是一种很有前景的替代方法,但现有的方法往往难以应对周期较长的任务。为了解决这一局限性,我们引入了一种计算高效的概率确定性无限自动机(PDFA)学习方法,它能直接从演示中捕捉任务结构和专家偏好。我们的方法可以推断出子目标及其时间依赖关系,从而生成领域专家易于理解和调整的可解释任务规范。我们通过涉及物体操作任务的实验验证了我们的方法,展示了我们的方法如何使机械臂有效地复制不同的专家策略,同时适应不断变化的条件。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Learning Task Specifications from Demonstrations as Probabilistic Automata
Specifying tasks for robotic systems traditionally requires coding expertise, deep domain knowledge, and significant time investment. While learning from demonstration offers a promising alternative, existing methods often struggle with tasks of longer horizons. To address this limitation, we introduce a computationally efficient approach for learning probabilistic deterministic finite automata (PDFA) that capture task structures and expert preferences directly from demonstrations. Our approach infers sub-goals and their temporal dependencies, producing an interpretable task specification that domain experts can easily understand and adjust. We validate our method through experiments involving object manipulation tasks, showcasing how our method enables a robot arm to effectively replicate diverse expert strategies while adapting to changing conditions.
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