The foundation of efficient robot learning
Name
psKaelbling_v1c.pdf
Description
Accepted version
Size
332.21 KB
Format
Adobe PDF
Checksum (MD5)
cb57a0405a695e85b1e5cf8ad174dea8
Author(s)
Kaelbling, Leslie P
Date Issued
August 2020
Journal
Science
Publisher
American Association for the Advancement of Science (AAAS)
Citation
Kaelbling, Leslie Pack et al. "The foundation of efficient robot learning." Science 369, 6506 (August 2020): 915-916. © 2020 The Author
Version
Author's final manuscript
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Center for Brains, Minds, and Machines
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1126/science.aaz7597
