Digitalni repozitorij raziskovalnih organizacij Slovenije

Izpis gradiva
A+ | A- | Pomoč | SLO | ENG

Naslov:Transfer learning in robotics : An upcoming breakthrough? A review of promises and challenges
Avtorji:ID Jaquier, Noemie (Avtor)
ID Welle, Michael C. (Avtor)
ID Gams, Andrej, Institut Jožef Stefan (Avtor)
ID Yao, Kunpeng (Avtor)
ID Fichera, Bernardo (Avtor)
ID Billard, Aude (Avtor)
ID Ude, Aleš, Institut Jožef Stefan (Avtor)
ID Asfour, Tamim (Avtor)
ID Kragič, Danica (Avtor)
Datoteke:.pdf PDF - Predstavitvena datoteka, prenos (1,69 MB)
MD5: 484BBC7BF4B76AE45B49CD69CC40F2A1
 
Jezik:Angleški jezik
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:Logo IJS - Institut Jožef Stefan
Povzetek:Transfer learning is a conceptually-enticing paradigm in pursuit of truly intelligent embodied agents. The core concept— reusing prior knowledge to learn in and from novel situations—is successfully leveraged by humans to handle novel situations. In recent years, transfer learning has received renewed interest from the community from different perspectives, including imitation learning, domain adaptation, and transfer of experience from simulation to the real world, among others. In this paper, we unify the concept of transfer learning in robotics and provide the first taxonomy of its kind considering the key concepts of robot, task, and environment. Through a review of the promises and challenges in the field, we identify the need of transferring at different abstraction levels, the need of quantifying the transfer gap and the quality of transfer, as well as the dangers of negative transfer. Via this position paper, we hope to channel the effort of the community towards the most significant roadblocks to realize the full potential of transfer learning in robotics
Status publikacije:Objavljeno
Verzija publikacije:Objavljena publikacija
Poslano v recenzijo:29.11.2023
Datum sprejetja članka:04.07.2024
Datum objave:13.09.2024
Založnik:SAGE Publications
Leto izida:2024
Št. strani:21 str.
Izvor:ZDA
PID:20.500.12556/DiRROS-20517 Novo okno
UDK:007.5
ISSN pri članku:0278-3649
DOI:10.1177/02783649241273565 Novo okno
COBISS.SI-ID:208015875 Novo okno
Avtorske pravice:© The Author(s) 2024.
Datum objave v DiRROS:07.10.2024
Število ogledov:22
Število prenosov:501
Metapodatki:XML RDF-CHPDL DC-XML DC-RDF
:
Kopiraj citat
  
Objavi na:Bookmark and Share


Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše podrobnosti ali sproži prenos.

Gradivo je del revije

Naslov:The international journal of robotics research
Skrajšan naslov:Int. j. rob. res.
Založnik:The MIT Press
ISSN:0278-3649
COBISS.SI-ID:2800143 Novo okno

Gradivo je financirano iz projekta

Financer:EC - European Commission
Program financ.:HE
Številka projekta:101070596
Naslov:European ROBotics and AI Network
Akronim:euROBIN

Licence

Licenca:CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
Povezava:http://creativecommons.org/licenses/by/4.0/deed.sl
Opis:To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.
Začetek licenciranja:13.09.2024
Vezano na:Vor

Sekundarni jezik

Jezik:Slovenski jezik
Ključne besede:robotika, strojno učenje


Nazaj