arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.02622cs.HCcs.AI
收藏

基于GUI的交互式任务学习Agent中的有效人机协作

Towards Effective Human-AI Collaboration in GUI-Based Interactive Task Learning Agents

Carnegie Mellon University(卡内基梅隆大学)

Toby Jia-Jun Li, Jingya Chen, Tom M. Mitchell, Brad A. Myers

摘要:

我们认为,为智能代理提供可用和有用的交互式任务学习的一个关键挑战是促进有效的人机协作。我们回顾了过去5年来在设计、开发和研究SUGILITE系统方面所做的努力,讨论了将人工智能的最新进展与人机交互原则结合到混合主动交互和多模式交互中的问题,并总结了我们学到的经验教训。最后,我们确定了几个挑战和机遇,并描述了我们正在进行的工作

英文摘要:

We argue that a key challenge in enabling usable and useful interactive task learning for intelligent agents is to facilitate effective Human-AI collaboration. We reflect on our past 5 years of efforts on designing, developing and studying the SUGILITE system, discuss the issues on incorporating recent advances in AI with HCI principles in mixed-initiative interactions and multi-modal interactions, and summarize the lessons we learned. Lastly, we identify several challenges and opportunities, and describe our ongoing work

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑