Humans have a remarkable ability to learn continuously from th e environment and inner experience. One of the grand goals of robots is to build an artificial "lifelong learning" agent that can shape a cultivated understanding of the world from the current scene and previous knowledge via an autonomous lifelong development. It is challenging for the robot learning process to retain earlier knowledge when robots encounter new tasks or information. Recent advances in computer vision and deep -learning methods have been impressive due to large-scale data sets, such as ImageNet and COCO. However, robotic vision poses unique new challenges for applying visual algorithms developed from these computer vision data sets because they implicitly assume a fixed set of categories and time -invariant task distributions.

IROS 2019 Lifelong Robotic Vision: Object Recognition Challenge

Chen B.
;
Graffieti G.;Kumar S.;Lomonaco V.;Ma L.;Maltoni D.;Pellegrini L.;Wu J.;Wu M.;Xu Y.;Yang L.;
2020

Abstract

Humans have a remarkable ability to learn continuously from th e environment and inner experience. One of the grand goals of robots is to build an artificial "lifelong learning" agent that can shape a cultivated understanding of the world from the current scene and previous knowledge via an autonomous lifelong development. It is challenging for the robot learning process to retain earlier knowledge when robots encounter new tasks or information. Recent advances in computer vision and deep -learning methods have been impressive due to large-scale data sets, such as ImageNet and COCO. However, robotic vision poses unique new challenges for applying visual algorithms developed from these computer vision data sets because they implicitly assume a fixed set of categories and time -invariant task distributions.
Bae H.; Brophy E.; Chan R.H.M.; Chen B.; Feng F.; Graffieti G.; Goel V.; Hao X.; Han H.; Kanagarajah S.; Kumar S.; Lam S.-K.; Lam T.L.; Lan C.; Liu Q.; Lomonaco V.; Ma L.; Maltoni D.; Parisi G.I.; Pellegrini L.; Piyasena D.; Pu S.; She Q.; Sheet D.; Song S.; Son Y.; Wang Z.; Ward T.E.; Wu J.; Wu M.; Xie D.; Xu Y.; Yang L.; Yang Q.; Zhong Q.; Zhou L.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/769508
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 5
social impact