Robot Motor Skill Coordination with EM-based Reinforcement Learning

被引:131
|
作者
Kormushev, Petar [1 ]
Calinon, Sylvain [1 ]
Caldwell, Darwin G. [1 ]
机构
[1] Italian Inst Technol IIT, Adv Robot Dept, I-16163 Genoa, Italy
关键词
SYNERGIES; SYSTEMS;
D O I
10.1109/IROS.2010.5649089
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present an approach allowing a robot to acquire new motor skills by learning the couplings across motor control variables. The demonstrated skill is first encoded in a compact form through a modified version of Dynamic Movement Primitives (DMP) which encapsulates correlation information. Expectation-Maximization based Reinforcement Learning is then used to modulate the mixture of dynamical systems initialized from the user's demonstration. The approach is evaluated on a torque-controlled 7 DOFs Barrett WAM robotic arm. Two skill learning experiments are conducted: a reaching task where the robot needs to adapt the learned movement to avoid an obstacle, and a dynamic pancake-flipping task.
引用
收藏
页码:3232 / 3237
页数:6
相关论文
共 50 条
  • [41] EM-based channel estimation algorithms for OFDM
    Ma, XQ
    Kobayashi, H
    Schwartz, SC
    [J]. EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING, 2004, 2004 (10) : 1460 - 1477
  • [42] Sensing the Partner: Toward Effective Robot Tutoring in Motor Skill Learning
    Belgiovine, Giulia
    Rea, Francesco
    Barros, Pablo
    Zenzeri, Jacopo
    Sciutti, Alessandra
    [J]. SOCIAL ROBOTICS, ICSR 2020, 2020, 12483 : 296 - 307
  • [43] Improving Robot Motor Learning with Negatively Valenced Reinforcement Signals
    Navarro-Guerrero, Nicolas
    Lowe, Robert J.
    Wermter, Stefan
    [J]. FRONTIERS IN NEUROROBOTICS, 2017, 11 : 1 - 14
  • [44] Toward 'optimal' schemes of robot assistance to facilitate motor skill learning
    Basteris, Angelo
    Sanguineti, Vittorio
    [J]. 2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2011, : 2355 - 2358
  • [45] EM-Based Channel Estimation Algorithms for OFDM
    Xiaoqiang Ma
    Hisashi Kobayashi
    Stuart C. Schwartz
    [J]. EURASIP Journal on Advances in Signal Processing, 2004
  • [46] Accurate EM-Based Modeling of Cascode FETs
    Resca, Davide
    Lonac, Julio A.
    Cignani, Rafael
    Raffo, Antonio
    Santarelli, Alberto
    Vannini, Giorgio
    Filicori, Fabio
    [J]. IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2010, 58 (04) : 719 - 729
  • [47] A framework for the adaptive transfer of robot skill knowledge using reinforcement learning agents
    Malak, RJ
    Khosla, PK
    [J]. 2001 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS, 2001, : 1994 - 2001
  • [48] EM-Based Clustering Algorithm for Uncertain Data
    Kinoshita, Naohiko
    Endo, Yasunori
    [J]. KNOWLEDGE AND SYSTEMS ENGINEERING (KSE 2013), VOL 2, 2014, 245 : 69 - 81
  • [49] EM-based Radar Signal Processing and Tracking
    Nussbaum, Alan
    Keel, Byron
    Blair, William Dale
    Ramachandran, Umakishore
    [J]. 2021 IEEE RADAR CONFERENCE (RADARCONF21): RADAR ON THE MOVE, 2021,
  • [50] EM-Based Detection of Hardware Trojans on FPGAs
    Soell, Oliver
    Korak, Thomas
    Muehlberghuber, Michael
    Hutter, Michael
    [J]. 2014 IEEE INTERNATIONAL SYMPOSIUM ON HARDWARE-ORIENTED SECURITY AND TRUST (HOST), 2014, : 84 - 87