Improving robotics competitions for real-world evaluation of AI

John Anderson, Hansjoerg (Jacky) Baltes, Kuo Yang Tu

研究成果: 書貢獻/報告類型會議貢獻

12 引文 斯高帕斯(Scopus)

摘要

While embodied robotic applications have been a strong influence on moving artificial intelligence toward focussing on broad, robust solutions that operate in the real world, evaluating such systems remains difficult. Competition-based evaluation, using common challenge problems, is one of the major methods for comparing AI systems employing robotic embodiment. Competitions unfortunately tend to influence the creation of specific solutions that exploit particular rules rather than the broad and robust techniques that are hoped for, however, and physical embodiment in the real world also creates difficulties in control and repeatability. In this paper we discuss the positive and negative influences of competitions as a means of evaluating AI systems, and present recent work designed to improve such evaluations. We describe how improved control and repeatability can be achieved with mixed reality applications for challenge problems, and how competitions themselves can encourage breadth and robustness, using our rules for the FIRA HuroCup as an example.

原文英語
主出版物標題Experimental Design for Real-World Systems - Papers from the AAAI Spring Symposium
頁面1-8
頁數8
出版狀態已發佈 - 2009 十一月 5
事件Experimental Design for Real-World Systems - Papers from the AAAI Spring Symposium - Stanford, CA, 美国
持續時間: 2009 三月 232009 三月 25

出版系列

名字AAAI Spring Symposium - Technical Report
SS-09-03

其他

其他Experimental Design for Real-World Systems - Papers from the AAAI Spring Symposium
國家美国
城市Stanford, CA
期間2009/03/232009/03/25

ASJC Scopus subject areas

  • Artificial Intelligence

指紋 深入研究「Improving robotics competitions for real-world evaluation of AI」主題。共同形成了獨特的指紋。

引用此