An industrial perspective on robot learning Challenges and opportunities

被引：0

作者：

Wahrburg, Arne ^{[1
,2
]}

Listmann, Kim D. ^{[1
,3
]}

Enayati, Nima ^{[1
,2
]}

Kirsten, Rene ^{[1
,2
]}

机构：

[1] ABB, Baden, Switzerland

[2] ABB Forschungszentrum Deutschland, Wallstadter Str 59, D-68526 Ladenburg, Germany

[3] ABB Future Labs Switzerland, Segelhofstr 1K, CH-5405 Baden, Switzerland

来源：

ATP MAGAZINE | 2020年 / 11-12期

关键词：

robot learning; reinforcement learning; imitation learning; LEVEL;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Robot learning has been a very active field of research recently with impressive scientific results especially in the application of reinforcement learning to robotic tasks. From an industrial perspective, the rapid scientific developments promise reduced commissioning times, simplified programming, increased productivity, and cost reductions. We attempt to put the potential of this promising but sometimes overhyped technology in perspective by matching it to industrial requirements. Key challenges are presented and possible ways to tackle them are discussed.

引用

页码：56 / 63

页数：8

共 24 条

[1]

Berkenkamp F, 2017, ADV NEUR IN, V30

[2]

Berner Christopher, 2019, arXiv

[3] A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials [J].

Chatzilygeroudis, Konstantinos ;

Vassiliades, Vassilis ;

Stulp, Freek ;

Calinon, Sylvain ;

Mouret, Jean-Baptiste .

IEEE TRANSACTIONS ON ROBOTICS, 2020, 36 (02) :328-347

[4]

Clever D., 2018, ROBOTIK SMART FACTOR

[5]

Dasari S., 2019, ARXIV191011215

[6]

Doerr Andreas, 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA), P5295, DOI 10.1109/ICRA.2017.7989622

[7]

Gealy DV, 2019, IEEE INT CONF ROBOT, P437, DOI [10.1109/ICRA.2019.8794236, 10.1109/icra.2019.8794236]

[8]

Haarnoja T., 2018, arXiv preprint arXiv:1812.05905

[9] Learning agile and dynamic motor skills for legged robots [J].

Hwangbo, Jemin ;

Lee, Joonho ;

Dosovitskiy, Alexey ;

Bellicoso, Dario ;

Tsounis, Vassilios ;

Koltun, Vladlen ;

Hutter, Marco .

SCIENCE ROBOTICS, 2019, 4 (26)

[10]

Inoue T, 2017, IEEE INT C INT ROBOT, P819, DOI 10.1109/IROS.2017.8202244

← 1 2 3 →