In recent years Reinforcement Learning (RL) has achieved remarkable results. Nonetheless RL algorithms prove to be unsuccessful in robotics applications where constraints satisfaction is involved, e.g. for safety. In this work we propose a control algorithm that allows to enforce constraints over a learned control policy. Hence we combine Nonlinear Model Predictive Control (NMPC) with control-state trajectories generated from the learned policy at each time step. We prove the effectiveness of our method on the Pendubot, a challenging underactuated robot.

Enforcing Constraints over Learned Policies via Nonlinear MPC: Application to the Pendubot / Turrisi, Giulio; BARROS CARLOS, Barbara; Cefalo, Massimo; Modugno, Valerio; Lanari, Leonardo; Oriolo, Giuseppe. - 53:2(2020), pp. 9502-9507. ((Intervento presentato al convegno 21st IFAC World Congress tenutosi a Berlin; Germany.

Enforcing Constraints over Learned Policies via Nonlinear MPC: Application to the Pendubot

Giulio Turrisi
;
Barbara Barros Carlos
;
Massimo Cefalo
;
Valerio Modugno
;
Leonardo Lanari
;
Giuseppe Oriolo
2020

Abstract

In recent years Reinforcement Learning (RL) has achieved remarkable results. Nonetheless RL algorithms prove to be unsuccessful in robotics applications where constraints satisfaction is involved, e.g. for safety. In this work we propose a control algorithm that allows to enforce constraints over a learned control policy. Hence we combine Nonlinear Model Predictive Control (NMPC) with control-state trajectories generated from the learned policy at each time step. We prove the effectiveness of our method on the Pendubot, a challenging underactuated robot.
File allegati a questo prodotto
File Dimensione Formato  
Turrisi_Enforcing_2020.pdf

accesso aperto

Note: https://doi.org/10.1016/j.ifacol.2020.12.2426
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 1.3 MB
Formato Adobe PDF
1.3 MB Adobe PDF Visualizza/Apri PDF

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/11573/1482348
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 3
social impact