The foundation of efficient robot learning
The foundation of efficient robot learning
复制标题
机器人高效学习的基础
DOI：
10.1126/science.aaz7597
复制
发表时间：
2020
期刊：
影响因子：
56.9
通讯作者：
L. Kaelbling
中科院分区：
文献类型：
--
作者：
L. Kaelbling
与生俱来的结构减少了数据需求并提高了稳健性在过去10年中，机器学习取得了巨大突破，导致计算机视觉和语言处理领域出现了改变游戏规则的应用程序。智能机器人领域渴望建造能够在各种环境中执行广泛任务的机器人，具有一般人类水平的智能，但这些突破尚未带来革命性的变化。一个关键的困难是，必要的学习依赖于数据，这些数据只能来自于在各种现实世界环境中的行为。这种数据的获取成本很高，因为通用机器人必须处理的情况存在巨大的变异性。它将需要新的算法技术、来自自然系统的灵感和多层次的机器学习的组合，才能用通用智能来彻底改变机器人学。
Innate structure reduces data requirements and improves robustness The past 10 years have seen enormous breakthroughs in machine learning, resulting in game-changing applications in computer vision and language processing. The field of intelligent robotics, which aspires to construct robots that can perform a broad range of tasks in a variety of environments with general human-level intelligence, has not yet been revolutionized by these breakthroughs. A critical difficulty is that the necessary learning depends on data that can only come from acting in a variety of real-world environments. Such data are costly to acquire because there is enormous variability in the situations a general-purpose robot must cope with. It will take a combination of new algorithmic techniques, inspiration from natural systems, and multiple levels of machine learning to revolutionize robotics with general-purpose intelligence.
DOI：
10.1073/pnas.1903070116
发表时间：
2019-08-06
影响因子：
11.1
作者：
Belkin, Mikhail;Hsu, Daniel;Mandal, Soumik
通讯作者：
Mandal, Soumik