Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1019204

Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives


Vidaković, Josip; Jerbić, Bojan; Šekoranja, Bojan; Švaco, Marko; Šuligoj, Filip
Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives // 28th International Conference on Robotics in Alpe- Adria-Danube Region / Springer, Cham (ur.).
Cham, Njemačka: Springer International Publishing, 2019. str. 275-282 doi:10.1007/978-3-030-19648-6_32 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 1019204 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives

Autori
Vidaković, Josip ; Jerbić, Bojan ; Šekoranja, Bojan ; Švaco, Marko ; Šuligoj, Filip

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

ISBN
978-3-030-19648-6

Skup
28th International Conference on Robotics in Alpe- Adria-Danube Region

Mjesto i datum
Kaiserslautern, Njemačka, 19.- 21.06.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Robot learning from demonstration ; dynamical movement primitives ; constrained trajectory

Sažetak
We propose a model for learning robot task constrained movements from a finite number of observed human demonstrations. The model uses the variation between demonstrations to extract important parts of the movements and reproduce trajectories accordingly. Regions with low variability are reproduced in a constrained manner, while regions with higher variability are approximated more loosely to achieve shorter trajectories. The demonstrations are sampled into states and an initial state sequence is chosen by a minimum distance criterion. Then, a method for state variation analysis is proposed that weights the states according to its similarity to all the other states. A custom function is constructed based on the state-variability information. The time function is then coupled with a state driven dynamical system to reproduce the trajectories. We test the approach on typical two-dimensional task constrained trajectories with constrains on the beginning, in the middle and the end of the movement. The approach is further compared with the case of using a standard exponentially decayed time function.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Strojarstvo



POVEZANOST RADA


Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb

Poveznice na cjeloviti tekst rada:

doi link.springer.com

Citiraj ovu publikaciju:

Vidaković, Josip; Jerbić, Bojan; Šekoranja, Bojan; Švaco, Marko; Šuligoj, Filip
Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives // 28th International Conference on Robotics in Alpe- Adria-Danube Region / Springer, Cham (ur.).
Cham, Njemačka: Springer International Publishing, 2019. str. 275-282 doi:10.1007/978-3-030-19648-6_32 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Vidaković, J., Jerbić, B., Šekoranja, B., Švaco, M. & Šuligoj, F. (2019) Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives. U: Springer, C. (ur.)28th International Conference on Robotics in Alpe- Adria-Danube Region doi:10.1007/978-3-030-19648-6_32.
@article{article, editor = {Springer, C.}, year = {2019}, pages = {275-282}, DOI = {10.1007/978-3-030-19648-6\_32}, keywords = {Robot learning from demonstration, dynamical movement primitives, constrained trajectory}, doi = {10.1007/978-3-030-19648-6\_32}, isbn = {978-3-030-19648-6}, title = {Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives}, keyword = {Robot learning from demonstration, dynamical movement primitives, constrained trajectory}, publisher = {Springer International Publishing}, publisherplace = {Kaiserslautern, Njema\v{c}ka} }
@article{article, editor = {Springer, C.}, year = {2019}, pages = {275-282}, DOI = {10.1007/978-3-030-19648-6\_32}, keywords = {Robot learning from demonstration, dynamical movement primitives, constrained trajectory}, doi = {10.1007/978-3-030-19648-6\_32}, isbn = {978-3-030-19648-6}, title = {Task Dependent Trajectory Learning from Multiple Demonstrations Using Movement Primitives}, keyword = {Robot learning from demonstration, dynamical movement primitives, constrained trajectory}, publisher = {Springer International Publishing}, publisherplace = {Kaiserslautern, Njema\v{c}ka} }

Časopis indeksira:


  • Scopus


Citati:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font