@article{Zambelli:2016:10.1109/TCDS.2016.2624705,
author = {Zambelli, M and Demiris, Y},
doi = {10.1109/TCDS.2016.2624705},
journal = {IEEE Transactions on Cognitive and Developmental Systems},
pages = {113--126},
title = {Online multimodal ensemble learning using self-learned sensorimotor representations},
url = {http://dx.doi.org/10.1109/TCDS.2016.2624705},
volume = {9},
year = {2016}
}

Download

TY  - JOUR
AB  - Internal  models  play  a  key  role  in  cognitive  agentsby providing on the one hand predictions of sensory consequencesof  motor  commands  (forward  models),  and  on  the  other  handinverse   mappings   (inverse   models)   to   realise   tasks   involvingcontrol  loops,  such  as  imitation  tasks.  The  ability  to  predictand generate new actions in continuously evolving environmentsintrinsically  requiring  the  use  of  different  sensory  modalities  isparticularly  relevant  for  autonomous  robots,  which  must  alsobe  able  to  adapt  their  models  online.  We  present  a  learningarchitecture based on self-learned multimodal sensorimotor rep-resentations.  To  attain  accurate  forward  models,  we  propose  anonline  heterogeneous  ensemble  learning  method  that  allows  usto  improve  the  prediction  accuracy  by  leveraging  differences  ofmultiple  diverse  predictors.  We  further  propose  a  method  tolearn inverse models on-the-fly to equip a robot with multimodallearning skills to perform imitation tasks using multiple sensorymodalities.  We  have  evaluated  the  proposed  methods  on  aniCub  humanoid  robot.  Since  no  assumptions  are  made  on  therobot  kinematic/dynamic  structure,  the  method  can  be  appliedto  different  robotic  platforms.
AU  - Zambelli,M
AU  - Demiris,Y
DO  - 10.1109/TCDS.2016.2624705
EP  - 126
PY  - 2016///
SN  - 2379-8920
SP  - 113
TI  - Online multimodal ensemble learning using self-learned sensorimotor representations
T2  - IEEE Transactions on Cognitive and Developmental Systems
UR  - http://dx.doi.org/10.1109/TCDS.2016.2624705
UR  - http://hdl.handle.net/10044/1/42245
VL  - 9
ER  - 

Download