Document Detail

Robust Sensorimotor Representation to Physical Interaction Changes in Humanoid Motion Learning.
MedLine Citation:
PMID:  25029488     Owner:  NLM     Status:  Publisher    
This paper proposes a learning from demonstration system based on a motion feature, called phase transfer sequence. The system aims to synthesize the knowledge on humanoid whole body motions learned during teacher-supported interactions, and apply this knowledge during different physical interactions between a robot and its surroundings. The phase transfer sequence represents the temporal order of the changing points in multiple time sequences. It encodes the dynamical aspects of the sequences so as to absorb the gaps in timing and amplitude derived from interaction changes. The phase transfer sequence was evaluated in reinforcement learning of sitting-up and walking motions conducted by a real humanoid robot and compatible simulator. In both tasks, the robotic motions were less dependent on physical interactions when learned by the proposed feature than by conventional similarity measurements. Phase transfer sequence also enhanced the convergence speed of motion learning. Our proposed feature is original primarily because it absorbs the gaps caused by changes of the originally acquired physical interactions, thereby enhancing the learning speed in subsequent interactions.
Toshihiko Shimizu; Ryo Saegusa; Shuhei Ikemoto; Hiroshi Ishiguro; Giorgio Metta
Related Documents :
18531978 - Time-frequency detection of stridence in fricatives and affricates.
10512548 - Formant pattern ambiguity of vowel sounds.
9557978 - Frequency-shaped amplification changes the neural representation of speech with noise-i...
10992138 - Adaptive dispersion in vowel perception.
11325128 - The effect of basilar-membrane nonlinearity on the shapes of masking period patterns in...
2646208 - Outputs of paired gabor filters summed across the background frame of reference predict...
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2014-7-10
Journal Detail:
Title:  IEEE transactions on neural networks and learning systems     Volume:  -     ISSN:  2162-2388     ISO Abbreviation:  IEEE Trans Neural Netw Learn Syst     Publication Date:  2014 Jul 
Date Detail:
Created Date:  2014-7-16     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101616214     Medline TA:  IEEE Trans Neural Netw Learn Syst     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Separating signal from noise: the challenge of identifying useful biomarkers in sepsis.
Next Document:  Kernel Association for Classification and Prediction: A Survey.