Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloModel-Based Reinforcement Learning Variable Impedance Control for Human-Robot Collaboration
Anno di pubblicazione2020
Autore/iRoveda, Loris; Maskani, Jeyhoon; Franceschi, Paolo; Abdi, Arash; Braghin, Francesco; Molinari Tosatti, Lorenzo; Pedrocchi, Nicola
Affiliazioni autoriPolitecnico di Milano; Consiglio Nazionale delle Ricerche; Istituto Dalle Molle Di Studi Sull'intelligenza Artificiale
Autori CNR e affiliazioni
  • inglese
AbstractIndustry 4.0 is taking human-robot collaboration at the center of the production environment. Collaborative robots enhance productivity and flexibility while reducing human's fatigue and the risk of injuries, exploiting advanced control methodologies. However, there is a lack of real-time model-based controllers accounting for the complex human-robot interaction dynamics. With this aim, this paper proposes a Model-Based Reinforcement Learning (MBRL) variable impedance controller to assist human operators in collaborative tasks. More in details, an ensemble of Artificial Neural Networks (ANNs) is used to learn a human-robot interaction dynamic model, capturing uncertainties. Such a learned model is kept updated during collaborative tasks execution. In addition, the learned model is used by a Model Predictive Controller (MPC) with Cross-Entropy Method (CEM). The aim of the MPC+CEM is to online optimize the stiffness and damping impedance control parameters minimizing the human effort (i.e, minimizing the human-robot interaction forces). The proposed approach has been validated through an experimental procedure. A lifting task has been considered as the reference validation application (weight of the manipulated part: 10 kg unknown to the robot controller). A KUKA LBR iiwa 14 R820 has been used as a test platform. Qualitative performance (i.e, questionnaire on perceived collaboration) have been evaluated. Achieved results have been compared with previous developed offline model-free optimized controllers and with the robot manual guidance controller. The proposed MBRL variable impedance controller shows improved human-robot collaboration. The proposed controller is capable to actively assist the human in the target task, compensating for the unknown part weight. The human-robot interaction dynamic model has been trained with a few initial experiments (30 initial experiments). In addition, the possibility to keep the learning of the human-robot interaction dynamics active allows accounting for the adaptation of human motor system.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali-
RivistaJournal of intelligent & robotic systems
Attiva dal 1988
Editore: Kluwer Academic Publishers - London ;
Paese di pubblicazione: Paesi Bassi
Lingua: inglese
ISSN: 0921-0296
Titolo chiave: Journal of intelligent & robotic systems
Titolo abbreviato: J. intell. robot. syst.
Titolo alternativo: Journal of intelligent and robotic systems
Numero volume della rivista-
Fascicolo della rivista-
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85081916731)
Parole chiaveHuman-robot collaboration, Industry 4.0, Machine learning, Model-based reinforcement learning control, Variable impedance control
Link (URL, URI)
Titolo parallelo-
Scadenza embargo-
Data di accettazione19/02/2020
Note/Altre informazioni-
Strutture CNR
  • STIIMA — Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato
Moduli/Attività/Sottoprogetti CNR
  • DIT.AD008.064.001 : EURECA Development of system components for automated cabin and cargo installation
Progetti Europei
Model-Based Reinforcement Learning Variable Impedance Control for Human-Robot Collaboration (documento privato )
Tipo documento: application/pdf