Herding the Crowd: Using Automated Planning for Better Crowdsourced Planning

L. Manikonda, T. Chakraborti, Kartik Talamadupula, S. Kambhampati
{"title":"Herding the Crowd: Using Automated Planning for Better Crowdsourced Planning","authors":"L. Manikonda, T. Chakraborti, Kartik Talamadupula, S. Kambhampati","doi":"10.15346/HC.V4I1.2","DOIUrl":null,"url":null,"abstract":"One subclass of human computation applications are those directed at tasks that involve planning (e.g. tour planning) and scheduling (e.g. conference scheduling). Interestingly, work on these systems shows that even primitive forms of automated oversight on the human contributors helps in significantly improving the effectiveness of the humans/crowd. In this paper, we argue that the automated oversight used in these systems can be viewed as a primitive automated planner, and that there are several opportunities for more sophisticated automated planning in effectively steering crowdsourced planning. Straightforward adaptation of current planning technology is however hampered by the mismatch between the capabilities of human workers and automated planners. We identify and partially address two important challenges that need to be overcome before such adaptation of planning technology can occur: (i) interpreting inputs of the human workers (and the requester) and (ii) steering or critiquing plans produced by the human workers, armed only with incomplete domain and preference models. To these ends, we describe the implementation of AI-MIX, a tour plan generation system that uses automated checks and alerts to improve the quality of plans created by human workers.","PeriodicalId":92785,"journal":{"name":"Human computation (Fairfax, Va.)","volume":"16 1","pages":"25-46"},"PeriodicalIF":0.0000,"publicationDate":"2017-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Human computation (Fairfax, Va.)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.15346/HC.V4I1.2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 13

Abstract

One subclass of human computation applications are those directed at tasks that involve planning (e.g. tour planning) and scheduling (e.g. conference scheduling). Interestingly, work on these systems shows that even primitive forms of automated oversight on the human contributors helps in significantly improving the effectiveness of the humans/crowd. In this paper, we argue that the automated oversight used in these systems can be viewed as a primitive automated planner, and that there are several opportunities for more sophisticated automated planning in effectively steering crowdsourced planning. Straightforward adaptation of current planning technology is however hampered by the mismatch between the capabilities of human workers and automated planners. We identify and partially address two important challenges that need to be overcome before such adaptation of planning technology can occur: (i) interpreting inputs of the human workers (and the requester) and (ii) steering or critiquing plans produced by the human workers, armed only with incomplete domain and preference models. To these ends, we describe the implementation of AI-MIX, a tour plan generation system that uses automated checks and alerts to improve the quality of plans created by human workers.
群策群力:利用自动化规划实现更好的众包规划
人类计算应用程序的一个子类是那些涉及计划(例如旅行计划)和调度(例如会议调度)的任务。有趣的是,在这些系统上的工作表明,即使是对人类贡献者进行原始形式的自动监督,也有助于显著提高人类/群体的效率。在本文中,我们认为在这些系统中使用的自动化监督可以被看作是一个原始的自动化计划器,并且在有效地指导众包计划方面有几个更复杂的自动化计划的机会。然而,当前规划技术的直接适应受到人类工作人员和自动化规划人员能力不匹配的阻碍。我们确定并部分解决了在这种规划技术的适应发生之前需要克服的两个重要挑战:(i)解释人类工作者(和请求者)的输入和(ii)指导或批评人类工作者产生的计划,仅使用不完整的领域和偏好模型。为此,我们描述了AI-MIX的实现,这是一个旅行计划生成系统,使用自动检查和警报来提高人工创建的计划的质量。
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
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