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

Napredna pretraga

Pregled bibliografske jedinice broj: 1058177

Accelerating robot trajectory learning for stochastic tasks


Vidaković, Josip; Jerbić, Bojan; Šekoranja, Bojan; Švaco, Marko; Šuligoj, Filip
Accelerating robot trajectory learning for stochastic tasks // IEEE access, 1 (2020), 1-1 doi:10.1109/access.2020.2986999 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 1058177 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Accelerating robot trajectory learning for stochastic tasks

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

Izvornik
IEEE access (2169-3536) 1 (2020); 1-1

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Learning from demonstration ; Policy search ; Robot task learning ; Robot trajectory

Sažetak
Learning from demonstration provides ways to transfer knowledge and skills from humans to robots. Models based solely on learning from demonstration often have very good generalization capabilities but are not completely accurate when adapting to new scenarios. This happens especially when learning stochastic tasks because of the correspondence problem and unmodeled physical properties of tasks. On the other hand, reinforcement learning (RL) methods such as policy search have the capability to refine an initial skill through exploration, where the learning process is often very dependent on the initialization strategy and is efficient in finding only local solutions. These two approaches are, therefore, frequently combined. In this paper, we present how the iterative learning of tasks can be accelerated by a learning from demonstration (LfD) method based on the extraction of via-points. The paper provides an evaluation of the approach on two different primitive motion tasks.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo



POVEZANOST RADA


Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb

Poveznice na cjeloviti tekst rada:

doi ieeexplore.ieee.org

Citiraj ovu publikaciju:

Vidaković, Josip; Jerbić, Bojan; Šekoranja, Bojan; Švaco, Marko; Šuligoj, Filip
Accelerating robot trajectory learning for stochastic tasks // IEEE access, 1 (2020), 1-1 doi:10.1109/access.2020.2986999 (međunarodna recenzija, članak, znanstveni)
Vidaković, J., Jerbić, B., Šekoranja, B., Švaco, M. & Šuligoj, F. (2020) Accelerating robot trajectory learning for stochastic tasks. IEEE access, 1, 1-1 doi:10.1109/access.2020.2986999.
@article{article, year = {2020}, pages = {1-1}, DOI = {10.1109/access.2020.2986999}, keywords = {Learning from demonstration, Policy search, Robot task learning, Robot trajectory}, journal = {IEEE access}, doi = {10.1109/access.2020.2986999}, volume = {1}, issn = {2169-3536}, title = {Accelerating robot trajectory learning for stochastic tasks}, keyword = {Learning from demonstration, Policy search, Robot task learning, Robot trajectory} }
@article{article, year = {2020}, pages = {1-1}, DOI = {10.1109/access.2020.2986999}, keywords = {Learning from demonstration, Policy search, Robot task learning, Robot trajectory}, journal = {IEEE access}, doi = {10.1109/access.2020.2986999}, volume = {1}, issn = {2169-3536}, title = {Accelerating robot trajectory learning for stochastic tasks}, keyword = {Learning from demonstration, Policy search, Robot task learning, Robot trajectory} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Citati:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font