Robot Learning from Demonstration in Robotic Assembly: A Survey

被引：171
作者：
Zhu, Zuyuan [1 ]
Hu, Huosheng [1 ]
机构：
[1] Univ Essex, Sch Comp Sci & Elect Engn, Wivenhoe Pk, Colchester CO4 3SQ, Essex, England
来源：
ROBOTICS | 2018年 / 7卷 / 02期
关键词：
learning from demonstration; imitation learning; robotic assembly; machine learning;
D O I：
10.3390/robotics7020017
中图分类号：
TP24 [机器人技术];
学科分类号：
080202 ; 1405 ;
摘要：
Learning from demonstration (LfD) has been used to help robots to implement manipulation tasks autonomously, in particular, to learn manipulation behaviors from observing the motion executed by human demonstrators. This paper reviews recent research and development in the field of LfD. The main focus is placed on how to demonstrate the example behaviors to the robot in assembly operations, and how to extract the manipulation features for robot learning and generating imitative behaviors. Diverse metrics are analyzed to evaluate the performance of robot imitation learning. Specifically, the application of LfD in robotic assembly is a focal point in this paper.
引用
收藏
页数：25
相关论文
共 124 条
[81]  
NEMEC B, 2013, ADV ROB ICAR 2013 16, P1, DOI DOI 10.1109/ICAR.2013.6766568
[82]  
Nicolescu MN, 2007, IMITATION AND SOCIAL LEARNING IN ROBOTS, HUMANS AND ANIMALS: BEHAVIOURAL, SOCIAL AND COMMUNICATIVE DIMENSIONS, P407, DOI 10.1017/CBO9780511489808.027
[83]  
Niekum S., 2013, P ROBOTICS SCI SYSTE, DOI [10.15607/RSS.2013.IX.048, DOI 10.15607/RSS.2013.IX.048]
[84]  
Nottensteiner K, 2016, IEEE INT CONF ROBOT, P130, DOI 10.1109/ICRA.2016.7487125
[85]   Incremental learning of tasks from user demonstrations, past experiences, and vocal comments [J].
Pardowitz, Michael ;
Knoop, Steffen ;
Dillmann, Ruediger ;
Zoellner, Raoul D. .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2007, 37 (02) :322-332
[86]  
Pastor P., 2009, P 2009 IEEE INT C RO, P763, DOI DOI 10.1109/ROBOT.2009.5152385
[87]  
PETERNEL L, 2015, P IEEE INT C ROB AUT, P1497, DOI DOI 10.1109/ICRA.2015.7139387
[88]   Robotic assembly solution by human-in-the-loop teaching method based on real-time stiffness modulation [J].
Peternel, Luka ;
Petric, Tadej ;
Babic, Jan .
AUTONOMOUS ROBOTS, 2018, 42 (01) :1-17
[89]   Reinforcement learning of motor skills with policy gradients [J].
Peters, Jan ;
Schaal, Stefan .
NEURAL NETWORKS, 2008, 21 (04) :682-697
[90]   Robonaut task learning through teleoperation [J].
Peters, RA ;
Campbell, CL ;
Bluethmann, WJ ;
Huber, E .
2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-3, PROCEEDINGS, 2003, :2806-2811
45678910111213