Goal reasoning is a main objective for robot task execution. Here we propose a deep model for learning to infer a next goal, while performing an activity. Because predicting the next goal state requires a robot language, not comparable to sentences, we introduce a specific metric for optimization, which is related to the representation the robot has of the scene. Experiments of the proposed idea and method have been done at a warehouse with a humanoid robot performing tasks assisting a maintenance technician working at a production line.

Anticipating next goal for robot plan prediction / Alati, E.; Mauro, L.; Ntouskos, V.; Pirri, F.. - 1037:(2020), pp. 792-809. (Intervento presentato al convegno Intelligent Systems Conference, IntelliSys 2019 tenutosi a London; United Kingdom) [10.1007/978-3-030-29516-5_60].

Anticipating next goal for robot plan prediction

Alati E.
;
Mauro L.
;
Ntouskos V.
;
Pirri F.
2020

Abstract

Goal reasoning is a main objective for robot task execution. Here we propose a deep model for learning to infer a next goal, while performing an activity. Because predicting the next goal state requires a robot language, not comparable to sentences, we introduce a specific metric for optimization, which is related to the representation the robot has of the scene. Experiments of the proposed idea and method have been done at a warehouse with a humanoid robot performing tasks assisting a maintenance technician working at a production line.
2020
Intelligent Systems Conference, IntelliSys 2019
Deep learning; Next-goal deep prediction; Robot perception; Robot planning
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Anticipating next goal for robot plan prediction / Alati, E.; Mauro, L.; Ntouskos, V.; Pirri, F.. - 1037:(2020), pp. 792-809. (Intervento presentato al convegno Intelligent Systems Conference, IntelliSys 2019 tenutosi a London; United Kingdom) [10.1007/978-3-030-29516-5_60].
File allegati a questo prodotto
File Dimensione Formato  
Alati_Anticipating-next_2020.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 6.31 MB
Formato Adobe PDF
6.31 MB Adobe PDF   Contatta l'autore

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/11573/1389365
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 2
social impact